Finance
30 columns
200 rows
8 formats

Synthetic Bank Loan Repayment Patterns

This dataset provides detailed, anonymized records of bank loan origination, repayment, default, and prepayment patterns, enriched with borrower demographic and employment information. It is ideal for developing and validating credit scoring models, analyzing risk factors, and exploring repayment behaviors across diverse borrower segments. The data structure supports advanced analytics and machine learning applications in financial risk management.

last updated 22 Jul 2025
by GoMask

The brief that made it

Credit risk modeling and scorecard development

Sample rows

preview · 8 of 200 rows · all 30 columns

loan_idstring	borrower_employment_statusstring	interest_ratefloat	default_flagboolean	loan_purposestring	borrower_idstring	origination_datedate	loan_amountfloat	loan_term_monthsinteger	repayment_statusstring	repayment_completion_datedate	total_paid_principalfloat	total_paid_interestfloat	remaining_principalfloat	num_payments_madeinteger	num_payments_lateinteger	num_payments_missedinteger	prepayment_flagboolean	borrower_ageinteger	borrower_genderstring	borrower_marital_statusstring	borrower_education_levelstring	borrower_annual_incomefloat	borrower_employer_namestring	borrower_years_at_employerfloat	borrower_residence_citystring	borrower_residence_statestring	borrower_residence_postal_codestring	borrower_residence_countrystring	credit_score_at_originationinteger
LN00001	employed_full_time	7.25	false	debt_consolidation	B1001	2016-03-11	9500	36	current	blank	3400	681.5	6100	12	1	0	false	29	female	single	bachelor	59000	NexGen Solutions	2.5	Chicago	IL	60614	US	728
LN00002	employed_part_time	16.99	false	vacation	B1002	2019-07-23	2000	12	paid_off	2020-08-01	2000	317.8	0	12	0	0	false	22	male	single	associate	9500	Bistro Place	0.7	Austin	TX	78704	US	662
LN00003	employed_full_time	5.99	false	auto	B1003	2017-12-02	35000	60	current	blank	18420	3821.65	16580	28	1	0	false	34	female	married	bachelor	71000	BrightPath Inc	6.1	Seattle	WA	98115	US	742
LN00004	unemployed	11.5	true	medical	B1004	2021-01-18	12000	24	defaulted	2022-10-11	2500	962	0	4	2	4	false	41	male	divorced	high_school	0	blank	blank	Cleveland	OH	44109	US	512
LN00005	self_employed	3.8	false	home_improvement	B1005	2018-11-09	340000	360	current	blank	38000	14520	302000	26	0	0	false	48	male	married	master	176000	Greenline Realty	12.7	San Diego	CA	92103	US	792
LN00006	student	20.99	false	education	B1006	2015-05-22	700	6	paid_off	2015-11-30	700	78	0	6	0	0	false	19	other	single	high_school	0	blank	blank	Columbus	OH	43210	US	626
LN00007	self_employed	4.25	false	business	B1007	2018-04-20	105000	84	current	blank	33500	9540	71500	34	0	0	false	58	female	widowed	bachelor	260000	Zeno Consulting	18.2	Dallas	TX	75201	US	803
LN00008	employed_full_time	9.89	false	debt_consolidation	B1008	2022-08-16	5400	18	current	blank	1650	239	3750	5	0	0	false	31	female	married	bachelor	44000	Urban Core Media	1.5	Denver	CO	80203	US	695
LN00009	employed_full_time	6.25	false	home_improvement	B1009	2017-03-19	41000	48	paid_off	2021-03-25	41000	5689	0	48	0	0	false	36	male	married	master	96000	Omni Networks	7.2	Los Angeles	CA	90024	US	777
LN00010	retired	13.25	false	medical	B1010	2020-10-14	8800	24	current	blank	1800	318	7000	5	0	1	false	56	male	divorced	high_school	18500	blank	blank	St. Paul	MN	55105	US	648
LN00011	self_employed	4.05	false	home_improvement	B1011	2023-03-08	800000	360	current	blank	40000	14500	760000	4	0	0	false	39	male	married	master	790000	Horizon Group	11.8	Miami	FL	33142	US	876
LN00012	employed_full_time	10.8	false	auto	B1012	2022-06-26	13000	36	current	blank	3500	410	9500	8	1	0	false	27	female	single	bachelor	38000	TechNest	1.8	Atlanta	GA	30309	US	724
LN00013	employed_full_time	11.25	false	other	B1003	2020-09-01	11000	24	prepaid	2022-01-10	11000	890	0	19	0	0	true	34	female	married	bachelor	71000	BrightPath Inc	8.6	Seattle	WA	98115	US	751
LN00014	self_employed	7.5	true	business	B1013	2017-07-15	78000	60	defaulted	2021-11-21	8500	1972	0	10	2	6	false	43	male	divorced	associate	42000	Blue Ridge Craft	5.1	Portland	OR	97205	US	498
LN00015	employed_part_time	8.29	false	vacation	B1014	2016-09-30	3100	12	paid_off	2017-09-29	3100	276	0	12	1	0	false	24	female	single	associate	12500	Sunrise Cafe	0.9	Orlando	FL	32801	US	675
LN00016	self_employed	4.45	false	home_improvement	B1015	2022-12-23	190000	300	current	blank	7200	2106	182800	4	0	0	false	50	female	widowed	bachelor	148000	Peak Realty	14.4	Houston	TX	77002	US	769
LN00017	retired	0	false	other	B1016	2015-04-30	0	1	paid_off	2015-05-30	0	0	0	1	0	0	false	78	prefer_not_to_say	other	other	12000	blank	blank	Boise	ID	83702	US	355
LN00018	self_employed	4.15	false	business	B1017	2023-02-19	2300000	360	current	blank	65000	28900	2235000	3	0	0	false	60	male	married	doctorate	2300000	Vista Holdings	25.7	Boston	MA	02108	US	891
LN00019	unemployed	15.99	true	debt_consolidation	B1018	2018-02-10	17000	36	defaulted	2021-07-02	2100	687	0	5	2	5	false	38	female	divorced	high_school	0	blank	blank	Reno	NV	89501	US	411
LN00020	employed_full_time	3.85	false	home_improvement	B1019	2023-06-18	470000	360	current	blank	12000	4120	458000	3	0	0	false	54	male	married	bachelor	120000	Lexicon Partners	13.3	Charlotte	NC	28202	US	862

What the 200 rows show

from the 200-row sample

Unemployed (borrower employment status) stands out: 14 of its 16 rows have default_flag = true, against 13 of 183 for the rest.

14%default_flag = true
8.4median interest_rate
4repayment statuses
4borrower genders
5borrower marital statuses
6borrower education levels

Default flag rate by borrower_employment_statusdefault_flag = true

interest_rate199 rows, in bands of 10

Median 8.4, from 0.0 to 100.0.

loan_purpose199 rows with a value · 1 left blank

auto36
home_improvement35
medical29
debt_consolidation24
vacation24
business24
other14
education13

30 columns by typefrom the column list below

string 13
integer 6
float 7
date 2
boolean 2

Columns

30 columns in four groups

blueprint · 30 columns
column	type	description	example
Text 13 columns
`loan_id`	string	Unique identifier for each loan record.unique	LN00001
`borrower_id`	string	Unique identifier for each borrower.	B1001
`loan_purpose`	string	Purpose of the loan (e.g., debt_consolidation, home_improvement, auto, education, other).8 values	debt_consolidation
`repayment_status`	string	Current status of the loan repayment (e.g., current, paid_off, defaulted, prepaid).current · paid_off · defaulted · prepaid	current
`borrower_gender`	string	Gender of the borrower.male · female · other · prefer_not_to_say · optional	female
`borrower_marital_status`	string	Marital status of the borrower.single · married · divorced · widowed · other · optional	single
`borrower_education_level`	string	Highest education level attained by the borrower.6 values · optional	bachelor
`borrower_employment_status`	string	Current employment status of the borrower.7 values	employed_full_time
`borrower_employer_name`	string	Name of the borrower's employer (anonymized or masked).optional	NexGen Solutions
`borrower_residence_city`	string	City of the borrower's residence at loan origination.optional	Chicago
`borrower_residence_state`	string	State or province of the borrower's residence at loan origination.optional	IL
`borrower_residence_postal_code`	string	Postal code of the borrower's residence at loan origination.optional	60614
`borrower_residence_country`	string	Country of the borrower's residence at loan origination.optional	US
Numbers 13 columns
`loan_amount`	float	Original principal amount of the loan.0 or more	9500
`loan_term_months`	integer	Number of months for the loan term.1 or more	36
`interest_rate`	float	Annual interest rate applied to the loan (as a percentage, e.g., 5.5 for 5.5%).0 to 100	7.25
`total_paid_principal`	float	Total principal amount paid by the borrower up to the current date.0 or more	3400
`total_paid_interest`	float	Total interest amount paid by the borrower up to the current date.0 or more	681.5
`remaining_principal`	float	Outstanding principal amount remaining on the loan.0 or more	6100
`num_payments_made`	integer	Number of scheduled payments made by the borrower.0 or more	12
`num_payments_late`	integer	Number of payments made after the due date.0 or more	1
`num_payments_missed`	integer	Number of scheduled payments missed entirely.0 or more	0
`borrower_age`	integer	Age of the borrower at the time of loan origination.18 to 100	29
`borrower_annual_income`	float	Annual income of the borrower at the time of loan origination.0 or more	59000
`borrower_years_at_employer`	float	Number of years the borrower has been at their current employer.0 or more · optional	2.5
`credit_score_at_origination`	integer	Borrower's credit score at the time of loan origination.300 to 900	728
Dates and times 2 columns
`origination_date`	date	Date when the loan was originated.	2016-03-11
`repayment_completion_date`	date	Date when the loan was fully repaid, prepaid, or defaulted. Null if still active.optional	2020-08-01
True or false 2 columns
`default_flag`	boolean	Indicates whether the loan has defaulted (true) or not (false).	false
`prepayment_flag`	boolean	Indicates whether the loan was prepaid (true) or not (false).	false

Use it for

A finance dashboard
The default_flag rate, interest_rate by borrower_employment_status and a breakdown of loan_purpose. Excel, Power BI or Tableau.
Why do 27 of 199 rows have default_flag = true?
A root-cause class exercise
Hand out the rows and one question. The answer is in the data, not in the brief.
Loans200
LN000017.25employed…
LN0000411.5unemploy…
LN000147.5self_emp…
A software demo
Believable loans with borrower_id, origination_date and loan_amount to fill a screen in front of a buyer.

This dataset200 rows30 columns

Yours1,000 rows30 columnsborrower_residence_city: UK only

blueprint · synthetic-bank-loan-repayment-patterns

Behind this dataset

Same schema. As many rows as you need.

These 200 rows came out of a blueprint — 30 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

Loans span 12-120 months
Default and prepayment events represented
Borrower credit scores range 300-850
Each loan has a unique identifier

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

Open the blueprint in Data Factory

1 credit per row. New accounts start with 25 free credits.

Exports: CSV, JSON, JSONL, Parquet, SQL, Excel, TSV, XML
Licence: yours to use, including commercially
API slug: synthetic-bank-loan-repayment-patterns

What should your data show?

No signup. No card.

Sample rows

What the 200 rows show

Columns

Use it for

A finance dashboard

A root-cause class exercise

A software demo

Make it yours.

Same schema. As many rows as you need.

More in Finance

What should your data show?