Finance
17 columns
200 rows
8 formats

Credit Card Fraud Detection

This dataset provides detailed, labeled records of simulated credit card transactions, including transaction amounts, merchant and cardholder information, and fraud indicators. It is ideal for developing and benchmarking machine learning models aimed at detecting fraudulent activity and reducing financial risk in payment systems. The inclusion of transaction context and cardholder demographics supports advanced analytics and feature engineering.

opened 19 times
last updated 12 Jul 2025
by GoMask

The brief that made it

Training and benchmarking machine learning models for credit card fraud detection

Sample rows

preview · 8 of 200 rows · all 17 columns

transaction_idstring	entry_modestring	transaction_amountfloat	is_fraudboolean	transaction_citystring	card_numberstring	transaction_datetimedatetime	merchant_idstring	merchant_categorystring	transaction_typestring	transaction_statestring	transaction_countrystring	currency_codestring	is_internationalboolean	cardholder_idstring	cardholder_ageinteger	cardholder_genderstring
TXN000001	chip	37.18	false	New York	4532519236845291	2022-01-14T09:37:21	MRH00012	grocery	purchase	NY	USA	USD	false	CH0001	31	female
TXN000002	contactless	12.95	false	San Francisco	6011928374012458	2022-02-10T15:22:45	MRH00023	coffee_shop	purchase	CA	USA	USD	false	CH0002	24	male
TXN000003	online	243.67	false	Chicago	372812345678901	2022-03-19T21:37:08	MRH00034	electronics	purchase	IL	USA	USD	false	CH0003	29	female
TXN000004	online	5921	true	London	5105105105105100	2022-04-07T18:11:43	MRH00045	travel	purchase	blank	GBR	GBP	true	CH0004	54	male
TXN000005	contactless	61.2	false	Austin	4916603234567890	2022-05-12T13:02:22	MRH00056	fast_food	purchase	TX	USA	USD	false	CH0005	22	female
TXN000006	contactless	14.89	false	Boston	6011123456789012	2022-06-03T16:44:11	MRH00067	public_transport	purchase	MA	USA	USD	false	CH0006	19	male
TXN000007	manual	1100	true	Zurich	378282246310005	2022-07-15T08:05:52	MRH00078	jewelry	purchase	blank	CHE	CHF	true	CH0007	38	female
TXN000008	chip	19.49	false	Seattle	4539512345678901	2022-08-21T22:55:35	MRH00089	books	purchase	WA	USA	USD	false	CH0003	29	female
TXN000009	online	256.71	false	Los Angeles	5424000000000015	2022-09-30T11:26:00	MRH00023	electronics	purchase	CA	USA	USD	false	CH0008	33	male
TXN000010	contactless	8.15	false	Houston	4532015112830366	2022-10-18T17:45:16	MRH00090	coffee_shop	purchase	TX	USA	USD	false	CH0009	26	female
TXN000011	swipe	47	false	Atlanta	6011000990139424	2022-11-05T10:12:29	MRH00101	fast_food	purchase	GA	USA	USD	false	CH0010	21	male
TXN000012	chip	25.99	false	Philadelphia	4000056655665556	2022-12-25T13:35:08	MRH00112	books	purchase	PA	USA	USD	false	CH0011	23	female
TXN000013	manual	4000	true	Dubai	6011256789012346	2023-01-09T20:55:17	MRH00123	luxury_goods	purchase	blank	ARE	AED	true	CH0012	47	male
TXN000014	contactless	13.35	false	Paris	371449635398431	2023-02-14T08:48:23	MRH00134	public_transport	purchase	blank	FRA	EUR	true	CH0006	19	male
TXN000015	swipe	86.5	false	Miami	5200828282828210	2023-03-22T19:36:43	MRH00145	pharmacy	purchase	FL	USA	USD	false	CH0013	62	female
TXN000016	chip	31.75	false	Dallas	6011000995504101	2023-04-05T06:59:15	MRH00156	grocery	purchase	TX	USA	USD	false	CH0014	47	female
TXN000017	online	129.99	false	San Diego	60115564485789458	2023-05-16T16:44:19	MRH00167	clothing	purchase	CA	USA	USD	false	CH0015	39	female
TXN000018	manual	25000	true	Tokyo	5111111111111118	2023-06-28T03:30:02	MRH00178	automobile	purchase	blank	JPN	JPY	true	CH0016	66	other
TXN000019	online	18.99	false	Denver	4556737586899855	2023-07-03T12:13:57	MRH00189	coffee_shop	purchase	CO	USA	USD	false	CH0017	23	male
TXN000020	online	990	false	Toronto	6011987654321098	2023-08-13T15:23:47	MRH00201	electronics	purchase	blank	CAN	CAD	true	CH0001	31	female

What the 200 rows show

from the 200-row sample

Manual (entry mode) stands out: 29 of its 29 rows have is_fraud = true, against 6 of 171 for the rest.

18%is_fraud = true
57.7median transaction_amount
4transaction types
4cardholder genders
10currency codes
11transaction countries

Is fraud rate by entry_modeis_fraud = true

transaction_amount200 rows, in bands of 100k

Median 57.7, from 0.01 to 1,000,000.

transaction_city190 rows with a value · 10 left blank

Seattle11
Chicago10
Boston10
Los Angeles10
Dallas10
New York9
Austin8
Houston8
Dubai8
Paris8

17 columns by typefrom the column list below

string 12
integer 1
float 1
datetime 1
boolean 2

Columns

17 columns in four groups

blueprint · 17 columns
column	type	description	example
Text 12 columns
`transaction_id`	string	Unique identifier for each credit card transaction.unique	TXN000001
`card_number`	string	Anonymized credit card number associated with the transaction.	4532519236845291
`merchant_id`	string	Unique identifier for the merchant processing the transaction.	MRH00012
`merchant_category`	string	Category code describing the type of merchant (e.g., grocery, electronics, travel).	grocery
`transaction_type`	string	Type of transaction (e.g., purchase, withdrawal, refund).purchase · withdrawal · refund · payment · transfer	purchase
`entry_mode`	string	How the card was used (e.g., chip, swipe, online, contactless).chip · swipe · online · contactless · manual	chip
`transaction_city`	string	City where the transaction was processed.optional	New York
`transaction_state`	string	State or province where the transaction was processed.optional	NY
`transaction_country`	string	Country where the transaction was processed.11 countries	USA
`currency_code`	string	ISO 4217 currency code used for the transaction.10 codes	USD
`cardholder_id`	string	Anonymized unique identifier for the cardholder.	CH0001
`cardholder_gender`	string	Gender of the cardholder.male · female · other · unknown · optional	female
Numbers 2 columns
`transaction_amount`	float	Total amount of the transaction in the local currency.0.01 or more	37.18
`cardholder_age`	integer	Age of the cardholder at the time of the transaction.18 to 120 · optional	31
Dates and times 1 column
`transaction_datetime`	datetime	Date and time when the transaction occurred.	2022-01-14T09:37:21
True or false 2 columns
`is_international`	boolean	Indicates if the transaction was processed outside the cardholder's home country.	false
`is_fraud`	boolean	Label indicating whether the transaction was fraudulent (true) or genuine (false).	false

Use it for

A finance dashboard
The is_fraud rate, transaction_amount by entry_mode and a breakdown of transaction_city. Excel, Power BI or Tableau.
Why do 35 of 200 rows have is_fraud = true?
A root-cause class exercise
Hand out the rows and one question. The answer is in the data, not in the brief.
Transactions200
TXN00000137.18chip
TXN0000045921online
TXN0000071100manual
A software demo
Believable transactions with card_number, transaction_datetime and transaction_amount to fill a screen in front of a buyer.

This dataset200 rows17 columns

Yours1,000 rows17 columnstransaction_city: UK only

blueprint · credit-card-fraud-detection

Behind this dataset

Same schema. As many rows as you need.

These 200 rows came out of a blueprint — 17 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 balanced mix of fraudulent and legitimate transactions
Simulate varied transaction types and amounts
Timestamp and merchant category required for each entry
Anonymize customer identifiers

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: credit-card-fraud-detection

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?