Insurance
23 columns
200 rows
8 formats

Insurance Policy Renewal Prediction

This dataset provides a comprehensive view of insurance policy renewals, combining detailed policy attributes, customer demographics, claims history, payment behavior, and renewal outcomes. It is ideal for predictive modeling, customer retention analysis, and operational optimization in the insurance industry.

opened 8 times
last updated 20 Aug 2025
by GoMask

The brief that made it

Predicting likelihood of policy renewal for targeted retention campaigns

Sample rows

preview · 8 of 200 rows · all 23 columns

policy_idstring	policy_typestring	customer_tenure_yearsfloat	has_late_paymentsboolean	customer_occupationstring	customer_idstring	policy_start_datedate	policy_end_datedate	premium_amountfloat	payment_frequencystring	policy_statusstring	customer_ageinteger	customer_genderstring	customer_citystring	customer_statestring	customer_postal_codestring	customer_countrystring	num_claims_last_yearinteger	total_claim_amount_last_yearfloat	renewal_offer_sentboolean	renewal_offer_amountfloat	renewedboolean	renewal_datedate
POL0001	auto	4.2	false	software engineer	CUST001	2023-01-15	2024-01-14	740.25	annual	active	29	male	San Francisco	CA	94107	USA	0	0	true	755.2	true	2024-01-10
POL0002	home	7	false	bank teller	CUST002	2016-09-05	2023-09-04	2150	annual	expired	54	female	New York	NY	10005	USA	1	2500	true	2200	false	2023-09-02
POL0003	health	1.1	true	student	CUST003	2022-03-01	2023-03-01	590.5	monthly	active	23	female	Los Angeles	CA	90007	USA	0	0	false	blank	false	blank
POL0004	life	18.5	false	retired teacher	CUST004	2014-02-24	2024-02-23	7800	annual	active	62	male	Rome	RM	00185	Italy	0	0	true	7900	false	2024-02-20
POL0005	travel	2.5	false	nutritionist	CUST005	2023-05-12	2024-05-11	220	annual	active	41	female	Berlin	BE	10115	Germany	0	0	true	230	true	2024-05-08
POL0006	auto	0.8	true	unemployed	CUST006	2020-06-28	2021-06-27	0	monthly	cancelled	21	male	Chicago	IL	60616	USA	1	1500	false	blank	false	blank
POL0007	home	5	false	business owner	CUST007	2019-04-10	2024-04-09	3200.5	annual	active	37	male	Dubai	DU	00000	UAE	0	0	true	3250	true	2024-04-07
POL0008	health	2	true	designer	CUST008	2021-08-01	2022-08-01	650	monthly	expired	32	female	Paris	PAR	75001	France	0	0	false	blank	false	blank
POL0009	life	30	false	centenarian	CUST009	1994-11-15	2024-11-14	12000	semi-annual	active	74	male	Zurich	ZH	8001	Switzerland	0	0	true	11900	false	2024-11-12
POL0010	other	9.8	false	investment banker	CUST010	2019-07-21	2024-07-20	53900	annual	active	48	female	London	ENG	EC2M	UK	1	80000	true	55000	true	2024-07-18
POL0011	auto	1	true	student	CUST011	2022-10-22	2023-10-21	350	monthly	expired	19	female	Austin	TX	73301	USA	0	0	false	blank	false	blank
POL0012	health	5.1	false	factory worker	CUST012	2018-02-15	2023-02-14	880	annual	expired	39	male	Hamburg	HH	20095	Germany	2	1800	true	900	false	2023-02-13
POL0013	travel	1	true	tour guide	CUST013	2021-01-13	2022-01-12	110	annual	expired	27	male	Cape Town	WC	8000	South Africa	0	0	false	blank	false	blank
POL0014	other	7	false	artist	CUST014	2015-09-23	2022-09-22	9200	quarterly	expired	46	female	Rio de Janeiro	RJ	20031-050	Brazil	0	0	true	9500	true	2022-09-20
POL0015	auto	3	false	designer	CUST015	2023-06-18	2024-06-17	480	annual	active	35	female	Sydney	NSW	2000	Australia	0	0	true	495	true	2024-06-15
POL0016	health	2	false	bank teller	CUST016	2023-09-30	2024-09-29	670	quarterly	active	31	male	Boston	MA	02108	USA	2	1200	true	695	true	2024-09-25
POL0017	auto	0.5	true	student	CUST017	2022-04-17	2023-04-16	0	monthly	cancelled	22	male	Phoenix	AZ	85004	USA	1	500	false	blank	false	blank
POL0018	home	15.3	true	doctor	CUST018	2007-07-10	2022-07-09	8000	semi-annual	expired	65	female	Tokyo	TK	100-0001	Japan	1	5000	true	8100	false	2022-07-08
POL0019	travel	3.4	false	tour guide	CUST019	2023-01-27	2024-01-26	320	annual	active	45	male	Berlin	BE	10115	Germany	2	1200	true	335	true	2024-01-23
POL0020	life	20	false	retired doctor	CUST020	2002-05-20	2022-05-19	15000	annual	expired	71	female	Delhi	DL	110001	India	0	0	true	15500	false	2022-05-16

What the 200 rows show

from the 200-row sample

Life (policy type) stands out: mean customer_tenure_years is 17.4, against 4.6 for the rest.

28%has_late_payments = true
3.5median customer_tenure_years
3policy statuses
3customer genders
4payment frequencies
17customer countries

Mean customer_tenure_years by policy_type200 rows

customer_tenure_years200 rows, in bands of 5

Median 3.5, from 0.20 to 40.0.

customer_occupation199 rows with a value · 1 left blank

student27
nutritionist15
tour guide14
bank teller10
designer10
artist10
business owner9
factory worker9
doctor9
retired9

23 columns by typefrom the column list below

string 11
integer 2
float 4
date 3
boolean 3

Columns

23 columns in four groups

blueprint · 23 columns
column	type	description	example
Text 11 columns
`policy_id`	string	Unique identifier for each insurance policyunique	POL0001
`customer_id`	string	Unique identifier for each customer	CUST001
`policy_type`	string	Type of insurance policy (e.g., auto, home, life)6 values	auto
`payment_frequency`	string	Frequency of premium paymentsmonthly · quarterly · semi-annual · annual	annual
`policy_status`	string	Current status of the policyactive · expired · cancelled	active
`customer_gender`	string	Gender of the customermale · female · other · unknown	male
`customer_occupation`	string	Occupation or employment category of the customeroptional	software engineer
`customer_city`	string	City of residence for the customeroptional	San Francisco
`customer_state`	string	State or province of residence for the customeroptional	CA
`customer_postal_code`	string	Postal code of the customer's addressoptional	94107
`customer_country`	string	Country of residence for the customeroptional	USA
Numbers 6 columns
`premium_amount`	float	Amount paid for the policy premium0 or more	740.25
`customer_age`	integer	Age of the customer at the time of policy renewal18 to 120	29
`num_claims_last_year`	integer	Number of claims made by the customer in the previous year0 or more	0
`total_claim_amount_last_year`	float	Total monetary value of claims made in the previous year0 or more	0
`customer_tenure_years`	float	Number of years the customer has held policies with the insurer0 or more	4.2
`renewal_offer_amount`	float	Premium amount quoted in the renewal offer (if sent)0 or more · optional	755.2
Dates and times 3 columns
`policy_start_date`	date	Date when the policy started	2023-01-15
`policy_end_date`	date	Date when the policy is set to expire	2024-01-14
`renewal_date`	date	Date when the renewal decision was madeoptional	2024-01-10
True or false 3 columns
`has_late_payments`	boolean	Indicates if the customer had any late premium payments in the last year	false
`renewal_offer_sent`	boolean	Indicates if a renewal offer was sent to the customer	true
`renewed`	boolean	Label indicating whether the customer renewed the policy (target variable)	true

Use it for

An insurance dashboard
The has_late_payments rate, customer_tenure_years by policy_type and a breakdown of customer_occupation. Excel, Power BI or Tableau.
Why do the 27 life rows have a mean customer_tenure_years of 17.4?
A root-cause class exercise
Hand out the rows and one question. The answer is in the data, not in the brief.
Policies200
POL00014.2auto
POL00031.1health
POL00060.8auto
A software demo
Believable policies with customer_id, policy_type and policy_start_date to fill a screen in front of a buyer.

This dataset200 rows23 columns

Yours1,000 rows23 columnscustomer_city: UK only

blueprint · insurance-policy-renewal-prediction

Behind this dataset

Same schema. As many rows as you need.

These 200 rows came out of a blueprint — 23 columns with generation rules behind each one. Open it in Data Factory to retune a column, add your own, wire in foreign keys, and run it at the size you actually need.

Rules it was built with

Policy details and types captured
Customer profile data included
Renewal status labeled
Policy lapse reasons annotated

Rows1,000 rows10,000 rows100,000 rows1,000,000 rows

Open the blueprint in Data Factory

1 credit per row. Preview 20 rows free. Buy rows for the full run.

Exports: CSV, JSON, JSONL, Parquet, SQL, Excel, TSV, XML
Licence: yours to use, including commercially
API slug: insurance-policy-renewal-prediction

What should your data show?

No signup. No card.

Sample rows

What the 200 rows show

Columns

Use it for

An insurance dashboard

A root-cause class exercise

A software demo

Make it yours.

Same schema. As many rows as you need.

More in Insurance

What should your data show?