Finance
28 columns
200 rows
8 formats

Credit Approval Decision Workflow

This dataset provides detailed records of credit and loan applications, including applicant demographics, application details, decision outcomes, and annotated decision logic trails. It is designed to enable research in fairness, bias detection, and explainable AI by capturing both the reasoning behind decisions and any subsequent appeals. The dataset is ideal for developing and evaluating transparent, equitable credit decision systems.

last updated 22 Jul 2025
by GoMask

The brief that made it

Fairness and bias analysis in credit decisioning

Sample rows

preview · 8 of 200 rows · all 28 columns

application_idstring	decision_outcomestring	decision_confidence_scorefloat	fairness_flagboolean	applicant_address_statestring	applicant_idstring	application_datedate	loan_amountfloat	loan_purposestring	applicant_incomefloat	applicant_employment_statusstring	applicant_credit_scoreinteger	applicant_ageinteger	applicant_genderstring	applicant_race_ethnicitystring	applicant_marital_statusstring	applicant_dependentsinteger	applicant_address_streetstring	applicant_address_citystring	applicant_address_postal_codestring	applicant_address_countrystring	decision_datetimedatetime	decision_reason_codesstring	decision_annotatorstring	decision_logic_trailstring	appeal_requestedboolean	appeal_outcomestring	appeal_decision_datetimedatetime
APP0001	approved	0.91	false	TX	A1001	2022-09-12	12000.5	personal	36500	employed	660	28	female	white	single	1	324 Pinecrest Dr	Dallas	75201	USA	2022-09-14T13:32:11	sufficient_income,good_credit	auto_sys_01	income>30k,credit>600,low_debt	false	not_applicable	blank
APP0002	approved	0.87	false	ON	A1002	2021-05-10	62000	auto	80000	self-employed	700	37	male	asian	married	2	211 Maple Ave	Toronto	M5H2N2	Canada	2021-05-12T11:45:22	stable_income,credit_adequate	auto_sys_03	income>60k,credit>650,car_loan	false	not_applicable	blank
APP0003	denied	0.38	true	IL	A1003	2023-03-18	400	personal	0	unemployed	320	22	non-binary	hispanic	single	0	98 South Street	Chicago	60616	USA	2023-03-20T14:02:56	unemployed,low_income,poor_credit	auto_sys_04	income<5k,credit<400	true	upheld	2023-03-30T11:12:09
APP0004	approved	0.82	false	CA	A1004	2021-11-03	2500	education	5200	student	580	20	female	asian	single	0	401 University Rd	Berkeley	94720	USA	2021-11-04T10:31:44	education_loan,student_status	human_analyst_02	student,loan_purpose_education	false	not_applicable	blank
APP0005	approved	0.99	false	NY	A1005	2019-12-17	950000	home	310000	employed	950	51	male	white	married	4	67 West End Ave	New York	10023	USA	2019-12-18T12:54:37	high_income,excellent_credit,low_debt	vip_analyst	income>250k,credit>900,low_dti	false	not_applicable	blank
APP0006	approved	0.89	false	FL	A1006	2020-07-08	18750	auto	37800	employed	620	32	female	black	single	1	89 Glenwood St	Miami	33131	USA	2020-07-09T09:31:16	auto_loan,adequate_income,good_credit	auto_sys_02	income>35k,credit>600,car_loan	false	not_applicable	blank
APP0007	denied	0.46	true	TX	A1007	2022-02-19	9200	personal	17800	unemployed	415	34	prefer_not_to_say	latino	single	1	12 Lakeview Blvd	Houston	77002	USA	2022-02-20T14:11:33	low_income,unemployed,credit_below_threshold	auto_sys_07	income<20k,unemployed,credit<500	true	upheld	2022-03-03T10:10:11
APP0008	approved	0.97	false	CA	A1008	2020-11-12	850000	home	178000	employed	875	45	male	asian	married	3	145 Cedar Lane	San Francisco	94105	USA	2020-11-13T13:22:44	high_income,good_credit,home_equity	auto_sys_05	income>150k,credit>800,home_loan	false	not_applicable	blank
APP0009	denied	0.52	true	WI	A1009	2023-01-15	2750	education	6000	student	420	19	male	black	single	0	78 College Ave	Madison	53703	USA	2023-01-15T16:07:02	student,low_income,credit_below_threshold	auto_sys_10	student,income<10k,credit<500	false	not_applicable	blank
APP0010	approved	0.85	false	TX	A1010	2022-06-18	105000	home	74500	self-employed	760	33	female	white	married	2	22 Willow Way	Austin	78701	USA	2022-06-19T15:13:21	adequate_income,credit_good,home_loan	human_analyst_01	income>70k,credit>700,low_dti	false	not_applicable	blank
APP0011	denied	0.25	true	London	A1011	2023-04-21	3900	personal	22000	unemployed	310	41	male	middle_eastern	divorced	0	27 Riverside Dr	London	SW1A2AA	UK	2023-04-22T12:08:47	unemployed,low_income,poor_credit	auto_sys_09	income<25k,credit<350	false	not_applicable	blank
APP0012	approved	0.93	false	CA	A1012	2022-10-02	12900	personal	42000	employed	690	27	female	white	single	1	53 Oak Grove Rd	Los Angeles	90017	USA	2022-10-03T10:52:15	stable_income,good_credit	auto_sys_02	income>40k,credit>650,personal_loan	false	not_applicable	blank
APP0013	approved	0.83	false	TX	A1013	2020-04-18	1400	personal	33000	employed	630	29	male	latino	single	0	15 Walnut St	San Antonio	78205	USA	2020-04-19T09:04:14	adequate_income,credit_acceptable	auto_sys_08	income>30k,credit>600,personal_loan	false	not_applicable	blank
APP0014	approved	0.89	false	PA	A1014	2023-05-02	37000	auto	54500	employed	690	36	female	white	married	2	790 Main St	Philadelphia	19103	USA	2023-05-03T12:15:22	adequate_income,auto_loan,good_credit	human_analyst_03	income>50k,credit>650,car_loan	false	not_applicable	blank
APP0015	denied	0.23	true	NM	A1015	2023-01-07	570	personal	2000	unemployed	185	25	male	indigenous/native_american	single	0	13 Sycamore Rd	Albuquerque	87102	USA	2023-01-08T09:42:01	unemployed,low_income,poor_credit	auto_sys_11	income<5k,credit<200,unemployed	true	pending	2023-01-15T10:25:00
APP0016	approved	0.92	false	MA	A1016	2020-08-30	250000	home	120000	self-employed	820	48	male	white	married	3	62 Elm Street	Boston	02116	USA	2020-08-31T15:10:45	high_income,good_credit,home_loan	auto_sys_06	income>100k,credit>800,home_loan	false	not_applicable	blank
APP0017	approved	0.84	false	WA	A1017	2021-06-14	4900	personal	28000	employed	675	31	female	pacific_islander	single	1	78 Ocean View	Seattle	98101	USA	2021-06-15T11:09:49	stable_income,good_credit	auto_sys_12	income>25k,credit>650,personal_loan	false	not_applicable	blank
APP0018	approved	0.88	false	CA	A1018	2018-10-12	12000	auto	34000	employed	682	27	female	asian	single	0	8 Birch Rd	San Jose	95112	USA	2018-10-13T15:38:26	stable_income,auto_loan,credit_adequate	auto_sys_03	income>30k,credit>650,car_loan	false	not_applicable	blank
APP0019	denied	0.19	true	MI	A1019	2020-01-10	495	personal	8000	unemployed	290	56	other	black	divorced	0	900 Spruce Dr	Detroit	48226	USA	2020-01-11T14:21:10	low_income,unemployed,poor_credit	auto_sys_10	income<10k,credit<400,unemployed	false	not_applicable	blank
APP0020	approved	0.84	false	MI	A1020	2022-04-08	3200	education	15000	student	610	21	male	asian	single	0	16 Campus Cir	Ann Arbor	48109	USA	2022-04-09T11:41:23	student,education_loan,credit_good	human_analyst_04	student,loan_purpose_education,credit>600	false	not_applicable	blank

What the 200 rows show

from the 200-row sample

Denied (decision outcome) stands out: mean decision_confidence_score is 0.32, against 0.88 for the rest.

28%fairness_flag = true
0.84median decision_confidence_score
4loan purposes
4applicant marital statuses
4applicant address countries
4appeal outcomes

Mean decision_confidence_score by decision_outcome200 rows

decision_confidence_score200 rows, in bands of 0.1

Median 0.84, from 0.19 to 1.0.

applicant_address_state200 rows · top 10 of 33 values

TX37
CA22
ON19
BC9
MA8
MI8
AZ8
IL7
NY7
WA7

28 columns by typefrom the column list below

string 17
integer 3
float 3
date 1
datetime 2
boolean 2

Columns

28 columns in four groups

blueprint · 28 columns
column	type	description	example
Text 17 columns
`application_id`	string	Unique identifier for each credit/loan applicationunique	APP0001
`applicant_id`	string	Unique identifier for the applicant (anonymized if necessary)	A1001
`loan_purpose`	string	Purpose of the loan (e.g., home, auto, personal, education)4 purposes	personal
`applicant_employment_status`	string	Employment status of the applicant (e.g., employed, self-employed, unemployed, retired, student)employed · self-employed · unemployed · retired · student	employed
`applicant_gender`	string	Gender of the applicant (if available and permitted)male · female · non-binary · other · prefer_not_to_say · optional	female
`applicant_race_ethnicity`	string	Race or ethnicity of the applicant (if available and permitted)9 ethnicities · optional	white
`applicant_marital_status`	string	Marital status of the applicant4 statuses · optional	single
`applicant_address_street`	string	Street address of the applicantoptional	324 Pinecrest Dr
`applicant_address_city`	string	City of the applicant's addressoptional	Dallas
`applicant_address_state`	string	State or province of the applicant's addressoptional	TX
`applicant_address_postal_code`	string	Postal code of the applicant's addressoptional	75201
`applicant_address_country`	string	Country of the applicant's address4 countries · optional	USA
`decision_outcome`	string	Final decision outcome (approved, denied, pending, withdrawn)approved · denied · pending · withdrawn	approved
`decision_reason_codes`	string	Comma-separated list of standardized reason codes for the decision (e.g., 'low_income,poor_credit')optional	low_income,poor_credit
`decision_annotator`	string	Identifier of the human or automated system that made or annotated the decisionoptional	auto_sys_01
`decision_logic_trail`	string	Textual or encoded representation of the decision logic trail (e.g., rule sequence, model path, or explanation)optional	income<5k,credit<400
`appeal_outcome`	string	Outcome of the appeal process (if any): upheld, overturned, pending, not_applicableupheld · overturned · pending · not_applicable · optional	not_applicable
Numbers 6 columns
`loan_amount`	float	Requested loan or credit amount0 or more	12000.5
`applicant_income`	float	Annual income of the applicant0 or more	36500
`applicant_credit_score`	integer	Credit score of the applicant at the time of application0 to 1,000	660
`applicant_age`	integer	Age of the applicant in years18 or more	28
`applicant_dependents`	integer	Number of dependents the applicant has0 or more · optional	1
`decision_confidence_score`	float	Confidence score (0-1) of the decision, if available0 to 1 · optional	0.91
Dates and times 3 columns
`application_date`	date	Date the application was submitted	2022-09-12
`decision_datetime`	datetime	Timestamp when the application decision was made	2022-09-14T13:32:11
`appeal_decision_datetime`	datetime	Timestamp when the appeal decision was made (if applicable)optional	2023-03-30T11:12:09
True or false 2 columns
`fairness_flag`	boolean	Indicates if the decision was flagged for potential fairness or bias concernsoptional	false
`appeal_requested`	boolean	Indicates if the applicant requested an appeal of the decisionoptional	false

Use it for

A finance dashboard
The fairness_flag rate, decision_confidence_score by decision_outcome and a breakdown of applicant_address_state. Excel, Power BI or Tableau.
Why do the 56 denied rows have a mean decision_confidence_score of 0.32?
A root-cause class exercise
Hand out the rows and one question. The answer is in the data, not in the brief.
Applications200
APP00010.91approved
APP00030.38denied
APP00070.46denied
A software demo
Believable applications with applicant_id, application_date and loan_amount to fill a screen in front of a buyer.

This dataset200 rows28 columns

Yours1,000 rows28 columnsapplicant_address_street: UK only

blueprint · credit-approval-decision-workflow

Behind this dataset

Same schema. As many rows as you need.

These 200 rows came out of a blueprint — 28 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
Document decision criteria at each workflow stage
Record final decision and feedback
Simulate varied application volumes

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: credit-approval-decision-workflow

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?