I have a dataset that contains data from the past 5 years about employees that are members of a pension scheme. It contains data about how many members are leaving the scheme and how many are joining.
Sign in to like and favorite skills
I have a dataset that contains data from the past 5 years about employees that are members of a pension scheme. It contains data about how many members are leaving the scheme and how many are joining.
Generate a list of 40 ways I could ask colloquially about how many members are joining and how many are leaving the scheme. Include examples that consider either trends or examples that consider a particular point in time e.g latest. Include some examples that refer to specific years.
Format the output in a flat json format with no fields
Use the following questions as an example
"How many employees left the scheme in the last quarter?" "Does there tend to be more people joining the scheme than leaving?" "Which years did the most employees leave the scheme?"
I have a dataset that contains data from the past 5 years about employees that are members of a pension scheme . It contains data about how many members are leaving the scheme and how many are joining.
Generate a list of 40 ways I could ask colloquially how many members are joining the scheme, or how many members are leaving the scheme across different age groups. Include examples that consider either trends or examples that consider a particular time e.g latest. Include a mix of examples that refer to specific ages and examples that refer to age groups in general. Format the output in a flat json format with no fields
For example
"How many younger scheme members are leaving compared to older ones" "How is the number of younger scheme members vs older ones changing over time" "Are younger employees joining scheme more over time" "How many members over 30 are joining the scheme"
I have a dataset that contains data from the past 5 years about employees that are members of a pension scheme . It contains data about how many members are leaving the scheme and how many are joining.
Generate a list of 40 ways I could ask colloquially how many members are joining the scheme, or how many members are leaving the scheme across different genders. Include examples that consider either trends or examples that consider a particular time e.g latest. Include a mix of examples that refer to specific genders and examples that refer to gender in general. Only consider Male and Female genders. Format the output in a flat json format with no fields
Include different ways to refer to "scheme membership"
For example
"How many female scheme members are leaving compared to male ones" "How is the number of female scheme members vs male ones changing over time" "Are male employees joining scheme more over time" "How many male members are joining the scheme"
I have a dataset that contains data from the past 5 years about employees that are members of a pension scheme . It contains data about how many members have logged into their pension scheme online.
Generate a list of 40 ways I could ask colloquially how many members have logged in to access their pension account. Include examples that consider either trends or examples that consider a particular time e.g latest. Use a variety of different terminology to refer to online services and activity.
Format the output in a flat json format with no fields
For example
"How many scheme members have logged in online " "What is the trend of members logging into digital services over time?" "how many people logged in in the last month?" "how often are members checking their accounts online?" "What's the trend in members using online services?" "are people using web and app more over time"
I have a dataset that contains data from the past 5 years about employees that are members of a pension scheme . It contains data about how many members have logged into their pension scheme online.
Generate a list of 40 ways I could ask colloquially how many members have logged in to access their pension account across different age groups. Include examples that consider either trends or examples that consider a particular time e.g latest. Use a variety of different terminology to refer to online services and activity.
Format the output in a flat json format with no fields
For example
"How many young scheme members have logged in online " "What is the trend of older members logging into digital services over time?" "how many people under age 40 logged in in the last month?" "how often are members over 50 checking their accounts online compare to under 25s?" "How does the trend in young members using online services compare to older ones?" "are older people using web and app services more over time"
I have a dataset that contains data from the past 5 years about employees that are members of a pension scheme . It contains data about how many members have logged into their pension scheme online.
Generate a list of 40 ways I could ask colloquially how many members have logged in to access their pension account across different genders. Include examples that consider either trends or examples that consider a particular time e.g latest. Use a variety of different terminology to refer to online services and activity.
Format the output in a flat json format with no fields
For example
"How many female scheme members have logged in online " "What is the trend of female members logging into digital services over time?" "how many males logged in in the last month?" "how often are female members checking their accounts online compared to male?" "How does the trend in female members using online services compare to male ones?" "are women using web and app services more over time"
I have a dataset that contains data from the past 5 years about employees that are members of a pension scheme . It contains data about how many members have logged into their pension scheme online.
Generate a list of 40 ways I could ask colloquially how many members have logged in to access their pension account across different salary bands. Include examples that consider either trends or examples that consider a particular time e.g latest. Use a variety of different terminology to refer to online services and activity.
Format the output in a flat json format with no fields
For example
"How many members who earn less than 40k have logged in online " "What is the trend of lower earning members logging into digital services over time?" "how many high earners (70k+) logged in in the last month?" "how often are highly paid members checking their accounts online compared to those on lower salaries?" "How does the trend in members earning less 30k using online services compare to those earning over 50k?" "Are lower earners tending to use web and app services more over time"
I have a dataset that contains data from the past 5 years about employees that are members of a pension scheme . It contains data about how many members have logged into their pension scheme online.
Generate a list of 40 ways I could ask colloquially whether members who have been in the scheme for longer are more likely to access their pension account online. Include examples that consider either trends or examples that consider a particular time e.g latest. Use a variety of different terminology to refer to online services and activity.
Format the output in a flat json format with no fields
For example
"How many members who've been in the scheme less than a year have logged in online" "Do members who have been in scheme longer tend to log into digital services more ?" "how many relatively new members (<2 years in scheme) logged in in the last month?" "how often are long standing members checking their accounts online compared to newer members?"
I have a dataset that contains data from the past 5 years about employees that are members of a pension scheme . It contains data about how many members are in the scheme over time
Generate a list of 40 ways I could ask colloquially about the trend and counts of members in the scheme. Include examples that consider either trends or examples that consider a particular time e.g latest, Q1, Feb 2023, a year ago. Use a variety of different terminology to refer to online services and activity.
Format the output in a flat json list format with no fields
For example
"How many members were in scheme this time last year" "How is the rate of membership changing over time?" "How did the number of members change between 2021 and 2022?" "Were there any years in particular that saw a big rise in membership?"
I have a dataset that contains data from the past 5 years about employees that are members of a pension scheme . It contains data about how many members are in the scheme over time
Generate a list of 40 ways I could ask colloquially about how the number of members in the scheme varies across age groups. Include examples that consider either trends or examples that consider a particular time e.g latest, Q1, Feb 2023, a year ago. Format the output as code in a flat json list format with no fields
For example
"How many member in scheme are below 30 years old" "Is the scheme made up of younger members or older ones. How is that changing over time" "How many members were under 25 between 2021 and 2022?" "Were there any years in particular that saw a big rise in membership of over 50s?"
I have a dataset that contains data from the past 5 years about employees that are members of a pension scheme . It contains data about how many members are in the scheme over time
Generate a list of 40 ways I could ask colloquially about how the number of members in the scheme varies for different genders. Include examples that consider either trends or examples that consider a particular time e.g latest, Q1, Feb 2023, a year ago.
Format the output as code in a flat json list format with no fields
For example
"How many members in scheme are male" "Is the scheme made up of mostly female members or male ones. How is that changing over time" "How many female members were there between 2021 and 2022?" "Were there any years in particular that saw a big rise in membership of female members?"
I have a dataset that contains data from the past 5 years about employees that are members of a pension scheme . It contains data about how many members are in the scheme over time
Generate a list of 40 ways I could ask colloquially about how the number of members in the scheme varies across different salaries. Include examples that consider either trends or examples that consider a particular time e.g latest, Q1, Feb 2023, a year ago.
Format the output as code in a flat json list format with no fields
For example
"How many members in scheme earn less than 25k" "Is the scheme made up of mostly higher paid members (>60k) or lower earners? How is that changing over time" "How many members were there between 2021 and 2022 who were earning more than 30k?" "Were there any years in particular that saw a big rise in membership members earning <30k?" "what's the ratio of members at different salary levels, and what's the trend over time?"
I have a dataset that contains data from the past 5 years about employees that are members of a pension scheme . It contains data about how many members are in the scheme over time
Generate a list of 40 ways I could ask colloquially about how many members in the scheme have been in the scheme for a long time vs those who have only been in the scheme for a short period of time. Include examples that consider either trends or examples that consider a particular time e.g latest, Q1, Feb 2023, a year ago.
Don't use the word tenure, use a variety of different terms that mean something similar
Format the output as code in a flat json list format with no fields
For example
"How many members in scheme have been members for less than a year" "Is the scheme made up of mostly long standing members or newer ones? How is that changing over time" "How many members were there between 2021 and 2022 had been in the pension scheme for longer than 5 years at that point?" "Were there any years in particular where total membership was made up of mostly those who had been in the scheme for a long time?" "what's the ratio of members that have had their pension since 2010, 2015 etc. and what's the trend over time?"
I have a dataset that contains data from the past 5 years about employees that are members of a pension scheme . It contains data about how many members are in the scheme over time
Generate a list of 40 ways I could ask colloquially about how many members in the scheme are close to retirement compared to those that are further away. Include examples that consider either trends or examples that consider a particular time e.g latest, Q1, Feb 2023, a year ago.
Format the output as code in a flat json list format with no fields
For example
"How many members in scheme will retire in less than a year" "Is the scheme made up of mostly members close to retirement or those a long way from retirement? How is that changing over time" "How many members were there between 2021 and 2022 that were retiring within 5 years?" "Were there any years in particular where total membership was made up of mostly those members that are retiring soon?"
I have a dataset that contains data from the past 5 years about employees that are members of a pension scheme . It contains data about how many members have nominated a beneficiary in the event they pass away
Generate a list of 40 ways I could ask colloquially about the number of members in the scheme that have nominated a beneficiary. Include examples that consider either trends or examples that consider a particular time e.g latest, Q1, Feb 2023, a year ago. Don't make any comparisons with any other variables - only consider percentages, counts, trend etc.
Format the output as code in a flat json list format with no fields
For example
"How many members had nominated a beneficiary this time last year" "How is the rate of members nominating beneficiary changing over time?" "How did the number of members's who had filled in a beneficiary form change between 2021 and 2022?" "Were there any years in particular that saw a big rise people nominating beneficiaries?" "is there a general increasing trend of the number of members nominating beneficiaries?" "Are there many members that haven't nominated a beneficiary?"
I have a dataset that contains data from the past 5 years about employees that are members of a pension scheme . It contains data about how many members have nominated a beneficiary in the event they pass away
Generate a list of 40 ways I could colloquially ask about the number of members in the scheme that have nominated a beneficiary across different age groups. Include examples that consider either trends or examples that consider a particular time e.g latest, Q1, Feb 2023, a year ago. Make sure only ages are considered and not any other groupings or categories.
Format the output as code in a flat json list format with no fields
For example
"How many members over 50 had nominated a beneficiary this time last year" "How is the rate of members between 30-40 years old that nominate a beneficiary changing over time compare to other age groups?" "How did the number of younger members's who had filled in a beneficiary form change between 2021 and 2022?" "Were there any years in particular that saw a big rise younger people nominating beneficiaries?" "is there a general increasing trend of the number of members over a certain age nominating beneficiaries?" "Are there particular age groups where a large proportion of members haven't nominated a beneficiary?"
I have a dataset that contains data from the past 5 years about employees that are members of a pension scheme . It contains data about how many members have nominated a beneficiary in the event they pass away
Generate a list of 40 ways I could colloquially ask about the number of members in the scheme that have nominated a beneficiary across different genders i.e. male and female. Include examples that consider either trends or examples that consider a particular time e.g latest, Q1, Feb 2023, a year ago.
Include a mix of examples that refer to one gender, or compare both. Only refer to genders - don't include age or any other category groups. For example
"How many female members had nominated a beneficiary this time last year" "How is the rate of male members between years old that nominate a beneficiary changing over time compare to females?" "How did the number of women who had filled in a beneficiary form change between 2021 and 2022?" "Were there any years in particular that saw a big rise in men nominating beneficiaries?" "is there a general increasing trend of the number of members of a certain gender nominating beneficiaries?" "Is there a large proportion of females who haven't nominated a beneficiary compared to men?"
Format the output as code in a flat json list format with no fields
I have a dataset that contains data from the past 5 years about employees that are members of a pension scheme . It contains data about how many members have nominated a beneficiary in the event they pass away
Generate a list of 40 ways I could colloquially ask about the number of members in the scheme that have nominated a beneficiary across different salaries. Include examples that consider either trends or examples that consider a particular time e.g latest, Q1, Feb 2023, a year ago.
Include a mix of examples that refer to one salary, or a range. Only refer to salaries - don't include gender, age or any other category groups.
For example
"How many high earning (70k+) members had nominated a beneficiary this time last year" "How is the rate of members earning <30k that nominate a beneficiary changing over time compared to those earning over 30k?" "How did the number of members earning less than 25k who had filled in a beneficiary form change between 2021 and 2022?" "Were there any years in particular that saw a big rise in high earning members nominating beneficiaries?" "is there a general increasing trend of the number of members of a certain salary range nominating beneficiaries?" "Is there a large proportion of members with a higher income (80k+) who haven't nominated a beneficiary compared to lower ones?"
Format the output as code in a flat json list format with no fields
I have a dataset that contains data from the past 5 years about employees that are members of a pension scheme . It contains data about how many members have nominated a beneficiary in the event they pass away
Generate a list of 40 ways I could colloquially ask whether members who have been in the scheme for longer are more likely to have nominated a beneficiary. Include examples that consider either trends or examples that consider a particular time e.g latest, Q1, Feb 2023, a year ago.
Don't use the word tenure. Include a mix of examples that refer to a specific length of time they've been in the scheme, or a range of years.
For example
"How many members who've been in the scheme less than a year have nominated a beneficiary" "Do members who have been in scheme longer tend to be more likely to nominate a beneficiary?" "how many relatively new members (<2 years in scheme) have nominated a beneficiary?" "how many long standing members haven't filled in a beneficiary form compared to newer members?" "Is there a large proportion of members who have been members for a long time and haven't nominated a beneficiary?"
Format the output as code in a flat json list format with no fields
I have a dataset that contains data from the past 5 years about employees that are members of a pension scheme . It contains data about how many members have nominated a beneficiary in the event they pass away
Generate a list of 40 ways I could colloquially ask whether members who are closer to retirement are more likely to have nominated a beneficiary. Include examples that consider either trends or examples that consider a particular time e.g latest, Q1, Feb 2023, a year ago.
Include a mix of examples that refer to a specific length of time away from retirement, or a range of years (with a gap of minimum 5 years).
For example
"How many members who are due to retire in the next 5 years have nominated a beneficiary" "Do members who are closer to retirement tend to be more likely to nominate a beneficiary?" "how many members that are relatively close to retirement (<2 years) have nominated a beneficiary?" "how many members due to retire soon haven't filled in a beneficiary form compared to those a long way from retirement?" "Is there a large proportion of members who are due to retire and haven't nominated a beneficiary?"
Format the output as code in a flat json list format with no fields
I have a dataset that contains data from the past 5 years about employees that are members of a pension scheme . It contains data about how much of their salary members are regularly contributing to their pensions.
Generate a list of 40 ways I could colloquially ask how many members are making regular contributions at different amounts (e.g. <3%, 3-5%, 7-10%, 15%+ etc.). Don't include examples that make reference to time periods or trends examples that. Include examples that refer to Employer contributions and the number of members that are receiving these different amounts too.
For example
"How many members are contributing less than 3% of their salary to their pension on a regular basis" "What proportion of members are making very low contributions (<3%)?" "How many members are maximising their pension offering and contributing as much as they can?" "how many members are making large regular contributions compared to those who aren't contributing much at all?" "How much are most members making in contributions to their pensions on a regular basis?"
Format the output as code in a flat json list format with no fields
I have a dataset that contains data from the past 5 years about employees that are members of a pension scheme . It contains data about how much of their salary members are regularly contributing to their pensions.
Generate a list of 40 ways I could colloquially ask how member pension contributions (e.g. <3%, 3-5%, 7-10%, 15%+ etc.) differ across age groups. Don't include examples that make reference to time periods or trends. Include examples that refer to the amount companies are contributing and the number of members that are receiving these different amounts too.
For example
"How many young members (<30) are contributing less than 3% of their salary to their pension on a regular basis" "Which age groups of members are making very low contributions (<3%)?" "Are older members more likely to maximise their pension offering and contribute as much as they can than younger ones?" "how many members over 45 are making relatively large regular contributions compared to those who aren't contributing much at all?" "Which age group of members are making the largest contributions to their pensions on a regular basis?"
Format the output as code in a flat json list format with no fields
I have a dataset that contains data from the past 5 years about employees that are members of a pension scheme . It contains data about how much of their salary members are regularly contributing to their pensions.
Generate a list of 40 ways I could colloquially ask how member pension contributions (e.g. <3%, 3-5%, 7-10%, 15%+ etc.) differ between genders (male and female). Don't include examples that make reference to time periods or trends. Include examples that refer to the amount companies are contributing and the number of members that are receiving these different amounts too.
For example
"How many females are contributing less than 3% of their salary to their pension on a regular basis" "How many male vs female members are making very low contributions (<3%)?" "Are female members more likely to maximise their pension offering and contribute as much as they can than male ones?" "how many female members are making relatively large regular contributions compared to those females who aren't contributing much at all?" "Which gender are making the largest contributions to their pensions on a regular basis?"
Format the output as code in a flat json list format with no fields
I have a dataset that contains data from the past 5 years about employees that are members of a pension scheme . It contains data about how much of their salary members are regularly contributing to their pensions.
Generate a list of 40 ways I could colloquially ask how member pension contributions (e.g. <3%, 3-5%, 7-10%, 15%+ etc.) differ between salaries. Don't include examples that make reference to time periods or trends.
For example
"How many higher earners (80k+) are contributing less than 3% of their salary to their pension on a regular basis" "How many members earning less than 35k are making very low contributions (<3%)?" "Are higher paid members more likely to maximise their pension offering and contribute as much as they can than lower paid ones?" "how many members with higher than average salaries (60k+) are making relatively large regular contributions compared to those who aren't contributing much at all?" "In which salary ranges are members making the largest contributions to their pensions on a regular basis?"
Format the output as code in a flat json list format with no fields
I have a dataset that contains data from the past 5 years about employees that are members of a pension scheme . It contains data about how much of their salary members are regularly contributing to their pensions.
Generate a list of 40 ways I could colloquially ask whether members who have been in the scheme for longer are more likely to make higher pension contributions (e.g. <3%, 3-5% 7-10%, 15%+ etc.). Don't include examples that make reference to time periods or trends.
For example
"How many members who have been in the scheme longer than 5 years are contributing less than 3% of their salary to their pension on a regular basis" "How many members who have been in the scheme for at least 2 years are making very low contributions (<3%)?" "Are long term members more likely to maximise their pension offering and contribute as much as they can than newer ones?" "how many longer standing members are making relatively large regular contributions compared to those who aren't contributing much at all?" "How many years do members tend to have been in the scheme in order to be making the largest contributions to their pensions?"
Format the output as code in a flat json list format with no fields
I have a dataset that contains data from the past 5 years about employees that are members of a pension scheme . It contains data about how much of their salary members are regularly contributing to their pensions.
INSTRUCTIONS
Generate a list of 40 ways I could colloquially ask whether members who are closer to retirement are more likely to make higher pension contributions (e.g. <3%, 3-5% 7-10%, 15%+ etc.). Don't include examples that make reference to time periods or trends.
Format the output as code in a flat json list format with no fields
EXAMPLE CONVERSATIONS
"How many members who are going to retire within the next 5 years are contributing less than 3% of their salary to their pension?" "How many members who retiring soon (<3 years) are making very low contributions (<3%)?" "Are members that are closer to retirement more likely to maximise their pension offering and contribute as much as they can than those further away from retirement?" "how many members very close to retirement are making relatively large regular contributions compared to those who aren't contributing much at all?" "How many years away from retirement do members tend to be in the scheme in order to be making the largest contributions to their pensions?"
I have a dataset that contains data from the past 5 years about employees that are members of a pension scheme. It contains data about how much members' pension funds are worth.
INSTRUCTIONS
Generate a list of 40 ways I could ask colloquially how much member's have saved in their pension funds and how they are changing in value over time. Include examples that make reference to a specific time period as well as trends in general. Use a variety of terms to refer to pension fund value.
Don't include reference to gender, age, or any other categorical groupings. Do not make reference to the total of all funds, and do not include references to market / economic factors.
Format the output as code in a flat json list format with no fields
EXAMPLE CONVERSATIONS
"How many members have more than 100k saved in their pension fund?" "How members have a retirement pot valued over 250k?" "How is the proportion of members with above average sized pension fund (250k) changing over time?" "Are the values of members' funds generally increasing over time?" "How many members had a pension worth between 50k-100k in 2022?"
I have a dataset that contains data from the past 5 years about employees that are members of a pension scheme. It contains data about how much members' pension funds are worth.
INSTRUCTIONS
Generate a list of 40 ways I could ask colloquially how much member's have saved in their pension funds and how it differs across age groups. Include examples that make reference to a specific time period as well as trends in general. Use a variety of terms to refer to pension fund value.
Do not make reference to the total of all funds, and do not include references to market / economic factors.
Format the output as code in a flat json list format with no fields
EXAMPLE CONVERSATIONS
"How many members under 30 have more than 100k saved in their pension fund?" "How younger members (<25) have a retirement pot valued over 250k?" "How is the proportion of older members (over 50) with above average sized pension fund (250k) changing over time?" "Are the values of 40-50 year old members' funds generally increasing over time?" "How many members over 50 had a pension worth between 50k-100k in 2022?"
I have a dataset that contains data from the past 5 years about employees that are members of a pension scheme. It contains data about how much members' pension funds are worth.
INSTRUCTIONS
Generate a list of 40 ways I could ask colloquially how much member's have saved in their pension funds and how it differs across genders (male and female). Include examples that make reference to a specific time period as well as trends in general. Use a variety of terms to refer to pension fund value.
Do not make reference to the total of all funds, ages or groupings other than gender. And do not include references to market / economic factors.
Format the output as code in a flat json list format with no fields
EXAMPLE CONVERSATIONS
"How many female members have more than 100k saved in their pension fund?" "How male members have a retirement pot valued over 250k?" "How is the proportion of female members with an above average sized pension fund (250k) changing over time?" "Are the values of female year old members' funds generally increasing over time?" "How many female members have a pension worth between 50k-100k compared to males?" "Is there a big difference in the value of pensions between men and women?"
I have a dataset that contains data from the past 5 years about employees that are members of a pension scheme. It contains data about how much members' pension funds are worth.
INSTRUCTIONS
Generate a list of 40 ways I could ask colloquially how much member's have saved in their pension funds and how it differs across salaries. Include examples that make reference to a specific time period as well as trends in general. Use a variety of terms to refer to pension fund value.
Do not make reference to the total of all funds, ages or groupings other than salaries. And do not include references to market / economic factors.
Format the output as code in a flat json list format with no fields
EXAMPLE CONVERSATIONS
"How many members earning less than 30k have more than 100k saved in their pension fund?" "How members with a salary under 25k have a retirement pot valued over 250k?" "How is the proportion of members earning between 50k-60k with an above average sized pension fund (250k) changing over time?" "Are the values of funds for employees earning over 50k generally increasing over time?" "How many lower earners (<25k) have a pension worth between 50k-100k compared to those earning over 70k?" "Is there a big difference in the value of pensions between lower earners (<30k) and higher earners (90k+)?"
I have a dataset that contains data from the past 5 years about employees that are members of a pension scheme. It contains data about how much members' pension funds are worth.
INSTRUCTIONS
Generate a list of 40 ways I could ask colloquially whether member's who have been in the scheme for longer, have saved more in their pension funds. Include examples that make reference to a specific time period as well as trends in general. Use a variety of terms to refer to pension fund value.
Do not make reference to the total of all funds, ages or gender groups. And do not include references to market / economic factors or tenure.
Format the output as code in a flat json list format with no fields
EXAMPLE CONVERSATIONS
"How many members who have been in the scheme for longer than 5 years have more than 100k saved in their pension fund?" "How long standing members have a retirement pot valued over 250k?" "What proportion of members have been in the scheme for long period of time with an above average sized pension fund (250k)?" "Are the values of funds for employees who have only been in the scheme for 3 years generally increasing over time?" "How many relatively new joiners have a pension worth between 50k-100k compared to those who's been in the scheme for longer?" "Is there a big difference in the value of pensions between people have just joined the scheme and those who've been members for a long time?"
I have a dataset that contains data from the past 5 years about employees that are members of a pension scheme. It contains data about how much members' pension funds are worth.
INSTRUCTIONS
Generate a list of 40 ways I could ask colloquially whether members who are closer to retirement, have saved more in their pension funds. Include examples that make reference to a specific time period as well as trends in general. Use a variety of terms to refer to pension fund value.
Do not make reference to the total of all funds, ages or gender groups. And do not include references to market / economic factors or tenure.
Format the output as code in a flat json list format with no fields
EXAMPLE CONVERSATIONS
"How many members who will retire in the next 5 years have more than 100k saved in their pension fund?" "Are there many members nearing retirement that have a retirement pot valued over 250k?" "What proportion of members close to retirement will have a pension fund size of at least 250k?" "Are the values of funds for employees who are within 3 years to retirement generally increasing over time?" "How many members are more than 15 years away from retirement have a pension worth between 50k-100k compared to those who are closer to retirement?" "Is there a big difference in the value of pensions between people who are close to retirement and those who are much further away?"
I have a dataset that contains data from the past 5 years about employees that are members of a pension scheme. It contains data about the total value of all members pensions combined.
INSTRUCTIONS
Generate a list of 40 ways I could ask colloquially how the total value of all members pensions and how that total is changing in value over time. Include examples that make reference to a specific time period as well as trends in general. Use a variety of terms to refer to total pension fund value e.g. assets under management, aum etc.
Don't include reference to gender, age, or any other categorical groupings. Do not include references to market / economic factors.
Format the output as code in a flat json list format with no fields
EXAMPLE CONVERSATIONS
"What is the combined value of all member's pensions?" "How has the total assets under management been changing over the past few years?" "Is the total value of all pensions increasing or decreasing over time, and at what rate?" "What was the total value of member's pensions in 2022?" "How has total assets under management changed between 2021 and 2024?"
I have a dataset that contains data from the past 5 years about employees that are members of a pension scheme. It contains data about the total value of all members pensions combined.
INSTRUCTIONS
Generate a list of 40 ways I could ask colloquially how the total value of all members pensions and how that total is changing in value over time and how it is split across different age groups. Include examples that make reference to a specific time period as well as trends in general. Use a variety of terms to refer to total pension fund value e.g. assets under management, aum etc.
Don't include reference to gender, or any other categorical groupings only age. Do not include references to market / economic factors.
Format the output as code in a flat json list format with no fields
EXAMPLE CONVERSATIONS
"What is the total value of all member's pensions who are <30?" "Is the split of total assets under management more for younger members or older ones?" "Is the total value of pensions for older members (>50) increasing or decreasing over time, and at what rate?" "What was the total value of member's pensions between the ages of 30-35 in 2022?" "What proportion of total assets under management was comprised of funds for members who are 60+ between 2021 and 2024?"
### Gender
I have a dataset that contains data from the past 5 years about employees that are members of a pension scheme. It contains data about the total value of all members pensions combined.
INSTRUCTIONS
Generate a list of 40 ways I could ask colloquially how the total value of all members pensions is split across different salaries and how that is changing in value over time. Include examples that make reference to a specific time period as well as trends in general. Use a variety of terms to refer to total pension fund value e.g. assets under management, aum etc.
Don't include reference to gender, or any other categorical groupings only salary. Do not include references to market / economic factors.
Format the output as code in a flat json list format with no fields
EXAMPLE CONVERSATIONS
"What is the total value of all member's pensions who are earning less than 30k?" "Is the split of total assets under management more for higher paid members or lower paid ones?" "Is the total value of pensions for high earners (80k+) increasing or decreasing over time, and at what rate?" "What was the total value of member's pensions who were earning between of 50-60k in 2022?" "What proportion of total assets under management was comprised of funds from members with an annual salary below 25k between 2021 and 2024?"
I have a dataset that contains data from the past 5 years about employees that are members of a pension scheme. It contains data about the total value of all members pensions combined.
INSTRUCTIONS
Generate a list of 40 ways I could ask colloquially how the total value of all members pensions is split across different genders (male and female) and how that is changing in value over time. Include examples that make reference to a specific time period as well as trends in general. Use a variety of terms to refer to total pension fund value e.g. assets under management, aum etc.
Don't include reference to gender, or any other categorical groupings only salary. Do not include references to market / economic factors.
Format the output as code in a flat json list format with no fields
EXAMPLE CONVERSATIONS
"What is the total value of all member's pensions who are female?" "Is the split of total assets under management more for male members or female ones?" "Is the total value of pensions for females increasing or decreasing over time, and at what rate?" "What was the total value of male member's pensions in 2022?" "What proportion of total assets under management was comprised of funds from male members between 2021 and 2024?"
I have a dataset that contains data from the past 5 years about employees that are members of a pension scheme. It contains data about the total value of all members pensions combined.
INSTRUCTIONS
Generate a list of 40 ways I could ask colloquially how the total value of all members pensions is split between those who have been in the scheme for longer vs relatively new members and how that is changing in value over time. Include examples that make reference to a specific time period as well as trends in general. Use a variety of terms to refer to total pension fund value e.g. assets under management, aum etc.
Don't include reference to gender, or any other categorical groupings only salary. Do not include references to market / economic factors.
Format the output as code in a flat json list format with no fields
EXAMPLE CONVERSATIONS
"What is the total value of all member's pensions who have been in the scheme for 5 years?" "Is the split of total assets under management more for members that have been in the scheme longer (10+ years) or newer members?" "Is the total value of pensions for long standing members increasing or decreasing over time, and at what rate?" "What was the total value of pensions for members who have been in the scheme for at least 3 years in 2022?" "What proportion of total assets under management was comprised of funds from newer members between 2021 and 2024?"
I have a dataset that contains data from the past 5 years about employees that are members of a pension scheme. It contains data about the total value of all members pensions combined.
INSTRUCTIONS
Generate a list of 40 ways I could ask colloquially how the total value of all members pensions is split between those members who are closer to retirement vs. those that are further away and how that is changing in value over time. Include examples that make reference to a specific time period as well as trends in general. Use a variety of terms to refer to total pension fund value e.g. assets under management, aum etc.
Don't include reference to gender, or any other categorical groupings only salary. Do not include references to market / economic factors.
Format the output as code in a flat json list format with no fields
EXAMPLE CONVERSATIONS
"What is the total value of all member's pensions who will be retiring in less than a year?" "Is the split of total assets under management more for members that will retire soon (<5 years) or for members that will retire in about 10-15 years?" "Is the total value of pensions for members due to retire increasing or decreasing over time, and at what rate?" "What was the total value of pensions for members who were 10-15 years away from retirement in 2022?" "What proportion of total assets under management was comprised of funds from members close to retirement between 2021 and 2024?"
I have a dataset that contains data from the past 5 years about employees that are members of a pension scheme. It contains data about how often members switch the funds that they are investing into.
INSTRUCTIONS
Generate a list of 40 ways I could ask colloquially how many members switch to different funds within their pension scheme across genders, and how that is changing over time. Include examples that make reference to a specific time period as well as trends in general. Use a variety of terms to refer to switching, e.g. changing, modifying, moving etc.
Do not use the term "pension funds" when referring to switching
Format the output as code in a flat json list format with no fields
EXAMPLE CONVERSATIONS
"how many female members switch to different funds?" "Are male members more likely to tend to keep investing in the same funds and has that been changing over the past few years?" "How many female members chose a different fund to invest in between 2021 -23?" "Is the likelihood of members changing the funds their pensions are invested in increasing or decreasing over time, how does it differ between men and women?" "How many male and female members changed the fund where their pension was invested in 2022?" "Did female members tend to change the funds their investments were allocated to between 2021 and 2024?"
I have a dataset that contains data from the past 5 years about employees that are members of a pension scheme. It contains data about how often members switch the funds that they are investing into.
INSTRUCTIONS
Generate a list of 40 ways I could ask colloquially how many members switch to different funds within their pension scheme across different age groups, and how that is changing over time. Include examples that make reference to a specific time period as well as trends in general. Use a variety of terms to refer to switching, e.g. changing, modifying, moving etc.
Do not use the term "pension funds" when referring to switching. Every output question should make reference age in some way.
Format the output as code in a flat json list format with no fields
EXAMPLE CONVERSATIONS
"how often do young members switch to different funds?" "Are older members (50+) more likely to keep investing in the same funds, and has that been changing over the past few years?" "How many members who are younger than 30 chose a different fund to invest in between 2021 -23?" "Is the likelihood of millennials changing the funds their pensions are invested in increasing or decreasing?" "How many members older than 60 changed the fund where their pension was invested in 2022?" "Do older members tend to change the funds their pension investments are allocated to more often than younger members?"
I have a dataset that contains data from the past 5 years about employees that are members of a pension scheme. It contains data about how often members switch the funds that they are investing into.
INSTRUCTIONS
Generate a list of 40 ways I could ask colloquially how many members switch to different funds within their pension scheme across genders, and how that is changing over time. Include examples that make reference to a specific time period as well as trends in general. Use a variety of terms to refer to switching, e.g. changing, modifying, moving etc.
Do not use the term "pension funds" when referring to switching
Format the output as code in a flat json list format with no fields
EXAMPLE CONVERSATIONS
"how many female members switch to different funds?" "Are male members more likely to tend to keep investing in the same funds and has that been changing over the past few years?" "How many female members chose a different fund to invest in between 2021 -23?" "Is the likelihood of members changing the funds their pensions are invested in increasing or decreasing over time, how does it differ between men and women?" "How many male and female members changed the fund where their pension was invested in 2022?" "Did female members tend to change the funds their investments were allocated to between 2021 and 2024?"
I have a dataset that contains data from the past 5 years about employees that are members of a pension scheme. It contains data about how often members switch the funds that they are investing into.
INSTRUCTIONS
Generate a list of 40 ways I could ask colloquially how many members switch to different funds within their pension scheme across salaries, and how that is changing over time. Include examples that make reference to a specific time period as well as trends in general. Use a variety of terms to refer to switching, e.g. changing, modifying, moving etc.
Do not use the term "pension funds" when referring to switching. Every output question should make reference to salary in some way.
Format the output as code in a flat json list format with no fields
EXAMPLE CONVERSATIONS
"how many high paid members switch to different funds?" "Are members who are paid less (<30k) more likely keep investing in the same funds and has that been changing over the past few years?" "How many above average earners chose a different fund to invest in between 2021 -23?" "Is the likelihood of members changing the funds their pensions are invested in increasing or decreasing over time, how does it differ by salary?" "How many low earners (<35k) changed the fund where their pension was invested in 2022?" "Did members who are paid more than 50k tend to change the funds their investments were allocated to between 2021 and 2024?"
I have a dataset that contains data from the past 5 years about employees that are members of a pension scheme. It contains data about how often members switch the funds that they are investing into.
INSTRUCTIONS
Generate a list of 40 ways I could ask colloquially if members are more likely to switch to different funds within their pension scheme the longer they've been in the scheme, and how that is changing over time. Include examples that make reference to a specific time period as well as trends in general. Use a variety of terms to refer to switching, e.g. changing, modifying, moving etc.
Do not use the term "pension funds" when referring to switching. Every output question should make reference to length of time in the scheme in some way.
Format the output as code in a flat json list format with no fields
EXAMPLE CONVERSATIONS
"how many long standing members switch to different funds?" "Are newer members more likely keep investing in the same funds and has that been changing over the past few years?" "How many members who had been in the scheme more than 5 years chose a different fund to invest in between 2021 -23?" "Is the likelihood of newer members changing the funds their pensions are invested in increasing or decreasing over time?" "How many members who've been in the scheme for less than a year changed the fund where their pension was invested in 2022?" "Did members who have been in the scheme between 5-10 years tend to change the funds their investments were allocated to between 2021 and 2024?"
I have a dataset that contains data from the past 5 years about employees that are members of a pension scheme. It contains data about how often members switch the funds that they are investing into.
INSTRUCTIONS
Generate a list of 40 ways I could ask colloquially if members are more likely to switch to different funds within their pension scheme if they are closer to retirement, and how that is changing over time. Include examples that make reference to a specific time period as well as trends in general. Use a variety of terms to refer to switching, e.g. changing, modifying, moving etc.
Do not use the term "pension funds" when referring to switching. Every output question should make reference to distance from retirement in some way.
Format the output as code in a flat json list format with no fields
EXAMPLE CONVERSATIONS
"how many members that are close to retirement switch to different funds?" "Are members that are about to retire more likely to keep investing in the same funds, and has that been changing over the past few years?" "How many members who are within 5 years to retirement chose a different fund to invest in between 2021 -23?" "Is the likelihood of newer members changing the funds their pensions are invested in increasing or decreasing as they get closer to retirement?" "How many members who were more than 15 years away from retirement changed the fund where their pension was invested in 2022?" "Did members that were a long way from retirement (more than 15 years) tend to change the funds their pension investments were allocated to between 2021 and 2024?"
How many members logging into web / app platforms have logged in recently (last 3 months)
I have a dataset that contains data from the past 5 years about employees that are members of a pension scheme. It contains data about how many members have used web or app services recently.
INSTRUCTIONS
Generate a list of 40 ways I could ask colloquially how many members have logged into digital platforms recently and how that is changing over time. Include examples that make reference to a specific time period as well as trends in general. Use a variety of terms to refer to online activity, e.g. logging in, online, using website, opening app etc.
Don't make reference to age, gender or any other category groupings. Don't reference economic events. Every output question should make reference to online usage in some way. Don't use the term 'platform', stick to more colloquial terms like website, app, online, web, internet etc.
Format the output as code in a flat json list format with no fields
EXAMPLE QUESTIONS
"how many members are using online services to manage their pension?" "What is the general trend of online activity over last 6 months?" "what proportion of members had been regularly logging into scottish widows website in 2022?" "how many members have used the app recently?" "Has online activity increased since 2018 or decreased?" "How did the frequency of usage of online services change between Jan - May 2022?" "How often are members using digital services for their pensions?"
I have a dataset that contains data from the past 5 years about employees that are members of a pension scheme. It contains data about how many members have used web or app services recently.
INSTRUCTIONS
Generate a list of 40 ways I could ask colloquially how many members have logged in online to the web or app recently across different genders, and how that is changing over time. Include examples that make reference to a specific time period as well as trends in general. Use a variety of terms to refer to online activity, e.g. logging in, online, using website, opening app etc.
Don't reference economic events. Every output question should make reference to online usage and gender in some way. Don't use the term 'platform', stick to more colloquial terms like website, app, online, web, internet etc.
Format the output as code in a flat json list format with no fields
EXAMPLE QUESTIONS
"how many females are using online services to manage their pension?" "What is the general trend of online activity between men and women over last 6 months?" "what proportion of male members had been regularly logging into scottish widows website in 2022?" "how many male members have used the app recently compared to females?" "Are men using online services more since 2018 or decreased?" "How did the frequency of usage of online services change between Jan - May 2022 for female members?" "How often are female members using digital services for their pensions vs male ones?"
I have a dataset that contains data from the past 5 years about employees that are members of a pension scheme. It contains data about how many members have used web or app services recently.
INSTRUCTIONS
Generate a list of 40 ways I could ask colloquially how many members have logged in online to the web or app recently across different salaries, and how that is changing over time. Include examples that make reference to a specific time period as well as trends in general. Use a variety of terms to refer to online activity, e.g. logging in, online, using website, opening app etc.
Don't reference economic events. Every output question should make reference to online usage and salary or pay in some way. Don't use the term 'platform', stick to more colloquial terms like website, app, online, web, internet etc.
Format the output as code in a flat json list format with no fields
EXAMPLE QUESTIONS
"how many lower earning members are using online services to manage their pension?" "What is the general trend of online activity between higher paid and low paid members over last 6 months?" "what proportion of members earning more than 50k had been regularly logging into scottish widows website in 2022?" "how many lower earners (<30k) have used the app recently?" "Are members who are paid more more likely to use online services since 2018?" "How did the frequency of usage of online services change between Jan - May 2022 for different salary groups?" "Is there a difference in members using digital services for their pensions depending on how much they earn?"
I have a dataset that contains data from the past 5 years about employees that are members of a pension scheme. It contains data about how many members have used web or app services recently.
INSTRUCTIONS
Generate a list of 40 ways I could ask colloquially how many members have logged in online to the web or app recently across different ages, and how that is changing over time. Include examples that make reference to a specific time period as well as trends in general. Use a variety of terms to refer to online activity, e.g. logging in, online, using website, opening app etc.
Don't reference economic events. Every output question should make reference to online usage and age in some way. Don't use the term 'platform', stick to more colloquial terms like website, app, online, web, internet etc.
Format the output as code in a flat json list format with no fields
EXAMPLE QUESTIONS
"how many younger members are using online services to manage their pension?" "What is the general trend of online activity between young and older members over last 6 months?" "what proportion of members under 35 had been regularly logging into scottish widows website in 2022?" "how many older members (50+) have used the app recently?" "Are young members (<30) using online services more since 2018 or less?" "How did the frequency of usage of online services change between Jan - May 2022 for different age groups?" "Is there a difference in members using digital services for their pensions depending on their age?"
I have a dataset that contains data from the past 5 years about employees that are members of a pension scheme. It contains data about how many members have used web or app services recently.
INSTRUCTIONS
Generate a list of 40 ways I could ask colloquially whether members are more likely to have logged in online to the web or app recently if they've been in the scheme longer, and how that is changing over time. Include examples that make reference to a specific time period as well as trends in general. Use a variety of terms to refer to online activity, e.g. logging in, online, using website, opening app etc.
Don't reference economic events. Every output question should make reference to online usage and length in scheme. Don't use the term 'platform', stick to more colloquial terms like website, app, online, web, internet etc.
Format the output as code in a flat json list format with no fields
EXAMPLE QUESTIONS
"how many newer members are using online services to manage their pension?" "What is the general trend of online activity between members who have been in the scheme a while vs newer ones over the last 6 months?" "what proportion of members who had been in the scheme for more than 5 years had been regularly logging into scottish widows website in 2022?" "how many new joiners (<1 year in the scheme) have used the app recently?" "Are members who have been in scheme longer more likely to use online services since 2018?" "How did the frequency of usage of online services change between Jan - May 2022 for people with different lengths of time in the scheme?" "Is there a difference in members using digital services for their pensions depending on how long they've been in the scheme?"
I have a dataset that contains data from the past 5 years about employees that are members of a pension scheme. It contains data about how many members have used web or app services recently.
INSTRUCTIONS
Generate a list of 40 ways I could ask colloquially whether members are more likely to have logged in online to the web or app recently if they are closer to retirement, and how that is changing over time. Include examples that make reference to a specific time period as well as trends in general. Use a variety of terms to refer to online activity, e.g. logging in, online, using website, opening app etc.
Don't reference economic events. Every output question should make reference to online usage and length in scheme. Don't use the term 'platform', stick to more colloquial terms like website, app, online, web, internet etc.
Format the output as code in a flat json list format with no fields
EXAMPLE QUESTIONS
"how many members that are close to retirement are using online services to manage their pension?" "What is the general trend of online activity between members who are retiring within a few years vs newer ones over the last 12 months?" "what proportion of members who are retiring in roughly 10-15 years had been regularly logging into scottish widows website in 2022?" "how many people who are due to retire have used the app recently?" "Are members who have closer to retirement more likely to use online services since 2018?" "How did the frequency of usage of online services change between Jan - May 2022 for people within 5 years of retirement?" "Is there a difference in members using digital services for their pensions depending on how close they are to retirement?"
I have a dataset that contains data from the past 5 years about employees that are members of a pension scheme. It contains data about the different types of payments into the pension scheme.
The different categories of payments are:
INSTRUCTIONS
Generate a list of 40 ways I could ask colloquially about the payments being made into the scheme, what types of payments they are (using the categories defined above), and how that is changing over time. Include examples that make reference to a specific time period as well as trends in general.
Don't reference economic events. Every output question should make reference to payments into the scheme and one or more of the categories above. If referencing 'contributions' it should always be compared to another category.
Format the output as code in a flat json list format with no fields
EXAMPLE QUESTIONS
"What are the largest types of payments being made into the scheme and how is that changing over time?" "How does the total amount of employer contributions compare to employee ones for the past 2 years?" "How much money are members transferring in from other schemes?" "Is the total amount of Employer contributions more than total transfers into the scheme?" "How is the total amount of member contributions changing over time relative to other payments into the scheme?" "What proportion of payments are from voluntary contributions (AVC)?" "Is the amount of money members are transferring into the scheme increasing over time?"
I have a dataset that contains data from the past 5 years about employees that are members of a pension scheme. It contains data about the different types of payments into the pension scheme.
The different categories of payments are:
INSTRUCTIONS
Generate a list of 40 ways I could ask colloquially about the payments being made into the scheme, how the different types of payments vary between gender (using the categories defined above), and how that is changing over time. Include examples that make reference to a specific time period as well as trends in general.
Don't reference economic events. Every output question should make reference to payments into the scheme and one or more of the categories above as well as gender (i.e. male or female). If referencing 'contributions' it should always be compared to another category.
Format the output as code in a flat json list format with no fields
EXAMPLE QUESTIONS
"What are the largest types of payments being made into the scheme by men and how is that changing over time?" "How does the total amount of employer contributions compare to employee ones for the past 2 years specifically for females?" "How much money are female members transferring in from other schemes compared to males?" "Is the total amount of Employer contributions to females more than their total transfers into the scheme?" "How is the total amount of member contributions from females changing over time relative to other payments into the scheme?" "What proportion of payments are from voluntary contributions (AVC) and how does that differ between males and females?" "Is the amount of money female members are transferring into the scheme increasing over time?"
I have a dataset that contains data from the past 5 years about employees that are members of a pension scheme. It contains data about the different types of payments into the pension scheme.
The different categories of payments are:
INSTRUCTIONS
Generate a list of 40 ways I could ask colloquially about the payments being made into the scheme, how the different types of payments vary across age groups (using the categories defined above), and how that is changing over time. Include examples that make reference to a specific time period as well as trends in general.
Don't reference economic events. Every output question should make reference to payments into the scheme and one or more of the categories above as well as age. If referencing 'contributions' it should always be compared to another category.
Format the output as code in a flat json list format with no fields
EXAMPLE QUESTIONS
"What are the largest types of payments being made into the scheme by younger members and how is that changing over time?" "How does the total amount of employer contributions compare to employee ones for the past 2 years specifically for older members?" "How much money are 30-40 year olds transferring in from other schemes?" "Is the total amount of Employer contributions to younger members (<30) more than their total transfers into the scheme?" "How is the total amount of member contributions from millennials changing over time relative to other payments into the scheme?" "What proportion of payments are from voluntary contributions (AVC) and how does that differ between different age groups?" "Is the amount of money 20-something year old members are transferring into the scheme increasing over time?"
I have a dataset that contains data from the past 5 years about employees that are members of a pension scheme. It contains data about the different types of payments into the pension scheme.
The different categories of payments are:
INSTRUCTIONS
Generate a list of 40 ways I could ask colloquially about the payments being made into the scheme, how the different types of payments vary across different salaries (using the categories defined above), and how that is changing over time. Include examples that make reference to a specific time period as well as trends in general.
Don't reference economic events. Every output question should make reference to payments into the scheme and one or more of the categories above as well as salary. If referencing 'contributions' it should always be with respect to 'total contributions' or 'sum of contributions' and be compared to another category.
Format the output as code in a flat json list format with no fields
EXAMPLE QUESTIONS
"What are the largest types of payments being made into the scheme by higher earners and how is that changing over time?" "How does the total amount of employer contributions compare to employee ones for the past 2 years specifically for lower earners (<£30k)?" "How much money are higher paid employees (£70k+) transferring in from other schemes?" "Is the total amount of Employer contributions to higher earning members more than their total transfers into the scheme?" "How is the total amount of member contributions from those with lower salaries changing over time relative to other payments into the scheme?" "What proportion of payments are from voluntary contributions (AVC) and how does that differ between different salary bands?" "Is the amount of money higher earning members are transferring into the scheme increasing over time?"
I have a dataset that contains data from the past 5 years about employees that are members of a pension scheme. It contains data about the different types of payments into the pension scheme.
The different categories of payments are:
INSTRUCTIONS
Generate a list of 40 ways I could ask colloquially about the payments being made into the scheme, how the different types of payments vary depending how members have been in the scheme (using the categories defined above), and how that is changing over time. Include examples that make reference to a specific time period as well as trends in general.
Don't reference economic events. Every output question should make reference to payments into the scheme and one or more of the categories above as well as how long they've been in the scheme. If referencing 'contributions' it should always be with respect to 'total contributions' or 'sum of contributions' and be compared to another category.
Format the output as code in a flat json list format with no fields
EXAMPLE QUESTIONS
"What are the largest types of payments being made into the scheme by people who have been in the scheme for 5 years or more and how is that changing over time?" "How does the total amount of employer contributions compare to employee ones for the past 2 years specifically for newer joiners?" "Are members more likely to transfer more money in from other schemes if they've been in the scheme for longer?" "Is the total amount of Employer contributions to newer members more than their total transfers into the scheme?" "How is the total amount of member contributions from those who've been in the scheme for a number of years changing over time relative to other payments into the scheme?" "What proportion of payments are from voluntary contributions (AVC) and how does that differ depending on how long member has been in scheme?" "Is the amount of money long standing members are transferring into the scheme increasing over time?"
I have a dataset that contains data from the past 5 years about employees that are members of a pension scheme. It contains data about the different types of payments into the pension scheme.
The different categories of payments are:
INSTRUCTIONS
Generate a list of 40 ways I could ask colloquially about the payments being made into the scheme, how the different types of payments vary depending how close members are to retirement (using the categories defined above), and how that is changing over time. Include examples that make reference to a specific time period as well as trends in general.
Don't reference economic events. Every output question should make reference to payments into the scheme and one or more of the categories above as well as how close / far they members are from retirement. If referencing 'contributions' it should always be with respect to 'total contributions' or 'sum of contributions' and be compared to another category (not with itself).
Format the output as code in a flat json list format with no fields
EXAMPLE QUESTIONS
"What are the largest types of payments being made into the scheme by people who are about to retire and how is that changing over time?" "How does the total amount of employer contributions compare to employee ones for the past 2 years specifically for those within 2 years of retirement?" "Are members more likely to transfer more money in from other schemes if they are close to retirement?" "Is the total amount of Employer contributions to members that are far from retirement more than their total transfers into the scheme?" "How is the total amount of member contributions from those roughly 10 years from retirement changing over time relative to other payments into the scheme?" "What proportion of payments are from voluntary contributions (AVC) and how does that differ depending on how soon members will retire?" "Is the amount of money members are transferring into the scheme increase as they get closer to retirement?"
I have a dataset that contains data from the past 5 years about employees that are members of a pension scheme. It contains data about the different types of payments that are going out of the pension scheme.
The different categories of payments out are:
INSTRUCTIONS
Generate a list of 40 ways I could ask colloquially about the payments being taken out of the scheme (using the categories defined above), and how that is changing over time. Include examples that make reference to a specific time period as well as trends in general.
Don't reference economic events or make comparisons to other categories such as age, gender or salary. Every output question should make reference to payments out of the scheme and one or more of the categories above. Use a variety of synonyms to refer to the categories 'retirement access' i.e. members accessing their pension at retirement, and 'death claims' i.e. pensions being claimed as part of life insurance etc.
Format the output as code in a flat json list format with no fields
EXAMPLE QUESTIONS
"What are the largest types of payments being made out of the scheme by people and how is that changing over time?" "How does the total amount funds being withdrawn to retired members compare to transfers out?" "What proportion of payments out were to family of members who had passed away in 2022?" "how much was paid out to members claiming their pensions at retirement in 2021?" "Is the total amount of funds being transferred out less than the amount being accessed for retirement?" "What are the different types of drawdowns from the scheme and how much did they change in the last 2 years?" "Is there an increase in the amount of money being paid to members who have retired and are claiming their pension? " "How is the level of transfers out of the scheme changing over time?"
I have a dataset that contains data from the past 5 years about employees that are members of a pension scheme. It contains data about the different types of payments that are going out of the pension scheme.
The different categories of payments out are:
INSTRUCTIONS
Generate a list of 40 ways I could ask colloquially about how the payments being taken out of the scheme (using the categories defined above) differ between genders, and how that is changing over time. Include examples that make reference to a specific time period as well as trends in general.
Don't reference economic events or make comparisons to other categories such as age, gender or salary. Every output question should make reference to payments out of the scheme and one or more of the categories above.
Use a different synonyms to refer to the categories 'retirement access' e.g. members accessing their pension at retirement, and 'death claims' e.g. pensions being claimed as part of life insurance etc.
Format the output as code in a flat json list format with no fields
EXAMPLE QUESTIONS
"What are the largest types of payments being made out of the scheme by female and how is that changing over time?" "How does the total amount funds being withdrawn to retired male members compare to transfers out?" "What proportion of payments out were to family of female members who had passed away in 2022?" "how much was paid out to male members claiming their pensions at retirement in 2021? compared to women" "Is the total amount of funds being transferred out less than the amount being accessed for retirement for females?" "What are the different types of drawdowns from the scheme and how do the differ between men and women?" "Is there an increase in the amount of money being paid to female members who have retired and are claiming their pension? " "How is the level of transfers out of the scheme changing over time between men and women?"
I have a dataset that contains data from the past 5 years about employees that are members of a pension scheme. It contains data about the different types of payments that are going out of the pension scheme.
The different categories of payments out are:
INSTRUCTIONS
Generate a list of 40 ways I could ask colloquially about how the payments being taken out of the scheme (using the categories defined above) differs across salaries, and how that is changing over time. Include examples that make reference to a specific time period as well as trends in general.
Don't reference economic events. Every output question should make reference to payments out of the scheme and one or more of the categories above.
Use different synonyms to refer to the categories 'retirement access' e.g. members accessing their pension at retirement, and 'death claims' e.g. pensions being claimed as part of life insurance etc.
Format the output as code in a flat json list format with no fields
EXAMPLE QUESTIONS
"What are the largest types of payments being made out of the scheme by higher earners and how is that changing over time?" "How does the total amount of funds being withdrawn to retired members with lower salaries compare to transfers out?" "What proportion of payments out were to family of well paid members who had passed away in 2022?" "how much was paid out to members earning less than £30k and claiming their pensions at retirement in 2021?" "Is the total amount of funds being transferred out less than the amount being accessed for retirement for those earning around £50k?" "What are the different types of drawdowns from the scheme and how do the differ between salaries?" "Is there an increase in the amount of money being paid to lower earners (<£30k) who have retired and are claiming their pension? " "How is the level of transfers out of the scheme changing over time between average earners and higher earners?"
I have a dataset that contains data from the past 5 years about employees that are members of a pension scheme. It contains data about the different types of payments that are going out of the pension scheme.
The different categories of payments out are:
INSTRUCTIONS
Generate a list of 40 ways I could ask colloquially about how the payments being taken out of the scheme (using the categories defined above) how they differ depending how the age of members.
Don't reference economic events or a specific time period. Every output question should make reference to payments out of the scheme and one or more of the categories above.
Use different synonyms to refer to the categories 'retirement access' e.g. members accessing their pension at retirement, and 'death claims' e.g. pensions being claimed as part of life insurance etc.
Format the output as code in a flat json list format with no fields
EXAMPLE QUESTIONS
"What are the largest types of payments being made out of the scheme by people who are under 20 and is that changing over time?" "How does the total amount of funds being withdrawn for death claims for younger members compare to transfers to other pensions?" "What proportion of payments out were to family of members who had passed away younger than average?" "how much was paid out to members who are between 20-35 years old?" "Is the total amount of funds being transferred out less than the amount being accessed for retirement for those who are over 50?" "What are the different types of drawdowns from the scheme and how do the differ depending on how old members are?" "Is there an increase in the amount of money being paid to older members (50+) that are claiming their pension? " "At what age are members typically accessing their retirement funds and how much is being paid out over time?"
I have a dataset that contains data from the past 5 years about employees that are members of a pension scheme. It contains data about the different types of payments that are going out of the pension scheme.
The different categories of payments out are:
INSTRUCTIONS
Generate a list of 40 ways I could ask colloquially about how the payments being taken out of the scheme (using the categories defined above) how they differ depending how close members are to retirement.
Don't reference economic events or a specific time period. Every output question should make reference to payments out of the scheme and one or more of the categories above.
Use different synonyms to refer to the categories 'retirement access' e.g. members accessing their pension at retirement, and 'death claims' e.g. pensions being claimed as part of life insurance etc.
Format the output as code in a flat json list format with no fields
EXAMPLE QUESTIONS
"What are the largest types of payments being made out of the scheme by people who are retiring in the next year and how is that changing over time?" "How does the total amount of funds being withdrawn for death claims for members who were close to retirement compare to transfers out?" "What proportion of payments out were to family of members who had passed away within 5 years of retirement?" "how much was paid out to members who are 10 years from retirement and claiming their pensions?" "Is the total amount of funds being transferred out less than the amount being accessed for retirement for those who are more than 10 years from retirement?" "What are the different types of drawdowns from the scheme and how do the differ depending on how close members are to retirement?" "Is there an increase in the amount of money being paid to recently retired members that are claiming their pension who had indicated they would retire 5 years later than they did? " "How is the level of transfers out of the scheme changing over time between new members and those who are nearing retirement?"
I have a dataset that contains data from the past 5 years about employees that are members of a pension scheme. It contains data about the ranges of different ages members have selected as their retirement date.
The different bands are:
INSTRUCTIONS
Generate a list of 40 ways I could ask colloquially about what age members have selected as their retirement date (using the categories defined above) and how that differs between genders.
Don't reference economic events. Don't reference changes over time, only consider the current / latest time period.
Do not reference statistical terms like mode, median or standard deviation etc.
Every output question should make reference to one of the following phrases in the question
Format the output as code in a flat json list format with no fields
EXAMPLE QUESTIONS
"What is the most common selected retirement age for women?" "How many female members are expecting to retire when they are older than 65, compare to men?" "What proportion of male members have indicated that they aim to retire before they reach 60?" "What's the lowest age that female members expect to retire by?" "What age do most female members expect to retire by compared to male members?" "Are the majority of members planning to retire before they are 60 or after, and how does that vary between men and women?" "What are the different proportions of NRA across genders? " "In general, what is least common normal retirement age for men in the scheme?"
### salary
I have a dataset that contains data from the past 5 years about employees that are members of a pension scheme. It contains data about the ranges of different ages members have selected as their retirement date.
The different bands are:
INSTRUCTIONS
Generate a list of 40 ways I could ask colloquially about what age members have selected as their retirement date (using the categories defined above) and how that differs across age groups.
Don't reference economic events. Don't reference changes over time, only consider the current / latest time period.
Do not reference statistical terms like mode, median or standard deviation etc.
Every output question should make reference to one of the following phrases in the question
Format the output as code in a flat json list format with no fields
EXAMPLE QUESTIONS
"What is the most common selected retirement age for younger members?" "How many young members are expecting to retire when they are older than 65, compare to older members?" "What proportion of members under 30 have indicated that they aim to retire before they reach 60?" "What's the lowest age that members between 20-30 expect to retire by?" "What age do most older members (50+) expect to retire?" "Are the majority of members under 30 planning to retire before they are 60 or after?" "What are the different proportions of NRA across age groups? " "Which age groups aim to retire before 60?" "Which age group in the scheme has specified the highest normal retirement age?"
I have a dataset that contains data from the past 5 years about employees that are members of a pension scheme. It contains data about the ranges of different ages members have selected as their retirement date.
The different bands are:
INSTRUCTIONS
Generate a list of 40 ways I could ask colloquially about what age members have selected as their retirement date (using the categories defined above) and how that differs by how long they've been in the scheme for.
Don't reference economic events. Don't reference changes over time, only consider the current / latest time period.
Do not reference statistical terms like mode, median or standard deviation etc.
Every output question should make reference to one of the following phrases in the question
Format the output as code in a flat json list format with no fields
EXAMPLE QUESTIONS
"What is the most common selected retirement age for members who have been in the scheme for more than 5 years?" "How many newer scheme members are expecting to retire when they are older than 65?" "What proportion of members who've been in the scheme for less than 10 years have indicated that they aim to retire before they reach 60?" "What's the lowest age that new scheme members expect to retire by?" "At what age do most long standing scheme members (15+ years) expect to retire?" "Are the majority of long-standing members planning to retire before they are 60 or after?" "What are the different proportions of NRA across different tenures? " "Typically how long have members that are aiming to retire before 60 been in the scheme for?" "Are newer members more likely to specify the highest normal retirement age or longer standing members?"
I have a dataset that contains data from the past 5 years about employees that are members of a pension scheme. It contains data about the ranges of different ages members have selected as their retirement date.
The different bands are:
INSTRUCTIONS
Generate a list of 40 ways I could ask colloquially about what age members have selected as their retirement date (using the categories defined above) and how that differs across salary ranges.
Don't reference economic events. Don't reference changes over time, only consider the current / latest time period.
Do not reference statistical terms like mode, median or standard deviation etc.
Every output question should make reference to one of the following phrases in the question
Format the output as code in a flat json list format with no fields
EXAMPLE QUESTIONS
"What is the most common selected retirement age for higher earning members?" "How many members earning less than 30k are expecting to retire when they are older than 65?" "What proportion of members on salaries between 50-80k have indicated that they aim to retire before they reach 60?" "What's the lowest age that high earning members (70k+) expect to retire by?" "At what age do most high earners (£70k or more) expect to retire?" "Are the majority of lower paid members (<30k) planning to retire before they are 60 or after?" "What are the different proportions of NRA across different salary ranges? " "What's the typical salary range for members aiming to retire before 60?" "Which salary range in the scheme has specified the highest normal retirement age?"
I have a dataset that contains data from the past 5 years about employees that are members of a pension scheme. It contains data about the ranges of different ages members have selected as their retirement date.
The different bands are:
INSTRUCTIONS
Generate a list of 40 ways I could ask colloquially about what age members have selected as their retirement date (using the categories defined above) and how that differs by how close they are to retirement.
Don't reference economic events. Don't reference changes over time, only consider the current / latest time period.
Do not reference statistical terms like mode, median or standard deviation etc.
Every output question should make reference to one of the following phrases in the question
every output question should also reference members proximity to retirement
Format the output as code in a flat json list format with no fields
EXAMPLE QUESTIONS
"What is the most common selected retirement age for members who are close to retirement?" "How many scheme members that are within 5 years of retirement are expecting to retire when they are older than 65?" "What proportion of members who are more than 10 years from retiring have indicated that they aim to retire before they reach 60?" "What's the lowest age that members close to retirement expect to retire by?" "At what age do most members who are further than 10 years from retiring expect to retire?" "Are the members planning to retire before they are 60 if they are less than 5 years from retirement?" "Typically are members that are aiming to retire before 60 more likely to be close to retirement?" "Are members who expect to retire after 70 more likely to be further away from retirement?"