Finance
24 columns
200 rows
8 formats

Loan Default Probability Dataset

This dataset provides detailed synthetic profiles of loan applicants and their loan applications, including demographic, financial, and credit information, along with default outcomes and predicted default probabilities. It is ideal for developing, benchmarking, and validating credit scoring and risk assessment models, and supports a wide range of analytics in financial services.

opened 9 times
last updated 12 Jul 2025
by GoMask

The brief that made it

Credit risk modeling and scorecard development

Sample rows

preview · 8 of 200 rows · all 24 columns

applicant_idstring	employment_statusstring	default_probabilityfloat	defaultedboolean	address_statestring	loan_idstring	application_datedate	loan_amountfloat	loan_term_monthsinteger	interest_ratefloat	loan_purposestring	annual_incomefloat	debt_to_income_ratiofloat	credit_scoreinteger	ageinteger	marital_statusstring	number_of_dependentsinteger	residential_statusstring	address_streetstring	address_citystring	address_postal_codestring	address_countrystring	previous_defaultsinteger	current_loans_countinteger
A10001	employed	0.09	false	NC	L10001	2018-03-26	275000	240	6.5	home	95000	29.3	762	46	married	2	mortgage	281 Willow Dr	Raleigh	27601	USA	0	1
A10002	employed	0.14	false	TX	L10002	2019-08-14	42000	36	10.2	auto	58000	37.7	669	34	single	0	rent	905 Summer St	Dallas	75201	USA	1	2
A10003	self-employed	0.12	false	IL	L10003	2020-05-16	29000	60	11.1	personal	71000	35.2	641	29	single	1	rent	127 George Ave	Chicago	60607	USA	0	2
A10004	self-employed	0.02	false	CA	L10004	2018-10-07	1600000	360	3.4	home	633000	21.4	848	61	married	3	own	12 Riverbank Pl	San Francisco	94114	USA	0	1
A10005	unemployed	0.73	true	GA	L10005	2021-03-30	8500	24	16.3	personal	2100	86.2	507	23	single	0	family	blank	Athens	30605	USA	2	1
A10006	employed	0.08	false	CO	L10006	2023-07-04	300000	180	5	home	112000	28.8	781	37	married	2	mortgage	450 Hickory Ln	Denver	80202	USA	0	1
A10007	self-employed	0.03	false	TX	L10007	2020-01-12	700000	360	2.7	business	188000	16.8	841	57	married	2	own	77 Main St	Houston	77019	USA	1	1
A10008	employed	0.12	false	AZ	L10008	2022-02-18	18000	36	13.4	auto	42000	33.1	653	31	single	1	rent	920 Elm St	Phoenix	85006	USA	1	1
A10009	self-employed	0.1	false	OR	L10009	2021-10-24	120000	120	8.3	business	98000	34.6	742	48	married	2	mortgage	613 Tiger Lily Ct	Portland	97202	USA	0	2
A10010	student	0.89	true	MI	L10010	2019-02-18	500	6	23.8	education	0	100	332	19	single	0	family	N/A	Ann Arbor	48104	USA	3	1
A10011	employed	0.13	false	NE	L10011	2022-12-09	12500	48	14.7	auto	37000	38.4	622	27	single	0	rent	684 Aspen Way	Omaha	68106	USA	1	2
A10012	employed	0.15	false	MN	L10012	2020-09-30	40000	60	9.8	personal	49000	42.1	601	39	divorced	1	rent	321 18th Ave	Minneapolis	55414	USA	0	1
A10013	employed	0.1	false	NC	L10013	2022-07-07	225000	180	7.1	home	89000	30.9	759	44	married	2	mortgage	59 Magnolia Blvd	Charlotte	28202	USA	0	1
A10014	unemployed	0.92	true	AZ	L10014	2021-06-23	32000	36	15.9	personal	1000	92.7	389	22	single	0	family	blank	Tempe	85281	USA	4	2
A10015	student	0.97	true	NY	L10015	2020-11-19	1800	12	17.7	other	0	100	355	18	single	0	family	blank	Ithaca	14850	USA	5	1
A10016	employed	0.13	false	OH	L10016	2019-06-13	22500	36	13.7	auto	48000	36.8	633	28	single	1	rent	442 Pine St	Columbus	43215	USA	0	1
A10017	employed	0.02	false	WA	L10017	2023-10-03	760000	360	2.8	home	225000	19.7	892	54	married	3	own	33 Overlook Rd	Seattle	98109	USA	0	1
A10018	self-employed	0.07	false	KY	L10018	2018-09-06	160000	180	6.1	business	119000	26.1	803	53	married	2	own	419 Market St	Louisville	40202	USA	0	2
A10019	self-employed	0.13	false	ID	L10019	2023-04-17	65000	60	8.5	business	75000	41.2	671	41	married	1	mortgage	1287 Oak Dr	Boise	83702	USA	1	2
A10020	student	0.86	true	FL	L10020	2019-11-26	2000	18	12.8	other	0	100	326	20	single	0	family	blank	Gainesville	32608	USA	4	2

What the 200 rows show

from the 200-row sample

Unemployed (employment status) stands out: mean default_probability is 0.94, against 0.23 for the rest.

26%defaulted = true
0.13median default_probability
5marital statuses
5residential statuses
6loan purposes
39,750median loan_amount

Mean default_probability by employment_status200 rows

default_probability200 rows, in bands of 0.1

Every row with default_probability of 0.5 or more has defaulted = true. None below it.

address_state196 rows with a value · 4 left blank

TX19
CA13
AZ11
OH11
FL10
NC9
WA9
CO8
IA8
IN7

24 columns by typefrom the column list below

string 11
integer 6
float 5
date 1
boolean 1

Columns

24 columns in four groups

blueprint · 24 columns
column	type	description	example
Text 11 columns
`applicant_id`	string	Unique identifier for each loan applicantunique	A10001
`loan_id`	string	Unique identifier for each loan applicationunique	L10001
`loan_purpose`	string	Purpose of the loan (e.g., home, auto, education, personal, business)6 values	home
`employment_status`	string	Current employment status of the applicant6 values	employed
`marital_status`	string	Marital status of the applicantsingle · married · divorced · widowed · other	married
`residential_status`	string	Type of residence (e.g., own, rent, mortgage, family, other)own · rent · mortgage · family · other	mortgage
`address_street`	string	Street address of the applicant's residenceoptional	281 Willow Dr
`address_city`	string	City of the applicant's residenceoptional	Raleigh
`address_state`	string	State or province of the applicant's residenceoptional	NC
`address_postal_code`	string	Postal code of the applicant's residenceoptional	27601
`address_country`	string	Country of the applicant's residenceoptional	USA
Numbers 11 columns
`loan_amount`	float	Total amount of the loan applied for (in local currency)0 or more	275000
`loan_term_months`	integer	Duration of the loan in months1 or more	240
`interest_rate`	float	Annual interest rate for the loan (percentage, e.g., 7.5 for 7.5%)0 to 100	6.5
`annual_income`	float	Applicant's reported annual income (in local currency)0 or more	95000
`debt_to_income_ratio`	float	Applicant's debt-to-income ratio (as a percentage, e.g., 35.5 for 35.5%)0 to 100	29.3
`credit_score`	integer	Applicant's credit score at the time of application300 to 900	762
`age`	integer	Applicant's age in years18 to 100	46
`number_of_dependents`	integer	Number of dependents supported by the applicant0 or more	2
`previous_defaults`	integer	Number of previous loan defaults by the applicant0 or more	0
`current_loans_count`	integer	Number of active loans held by the applicant at the time of application0 or more	1
`default_probability`	float	Predicted probability of default for this loan (between 0.0 and 1.0)0 to 1	0.09
Dates and times 1 column
`application_date`	date	Date when the loan application was submitted	2018-03-26
True or false 1 column
`defaulted`	boolean	Indicates if the applicant defaulted on this loan (true = defaulted, false = not defaulted)	false

Use it for

A finance dashboard
The defaulted rate, default_probability by employment_status and a breakdown of address_state. Excel, Power BI or Tableau.
Why do the 19 unemployed rows have a mean default_probability of 0.94?
A root-cause class exercise
Hand out the rows and one question. The answer is in the data, not in the brief.
Applicants200
A100010.09employed
A100050.73unemploy…
A100100.89student
A software demo
Believable applicants with loan_id, application_date and loan_amount to fill a screen in front of a buyer.

This dataset200 rows24 columns

Yours1,000 rows24 columnsaddress_street: UK only

blueprint · loan-default-probability-dataset

Behind this dataset

Same schema. As many rows as you need.

These 200 rows came out of a blueprint — 24 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

Include applicant demographics and credit history
Loan attributes: amount, term, purpose
Label as default or paid
Anonymize all sensitive data

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: loan-default-probability-dataset

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?