Credit Card Fraud Patterns

This dataset contains simulated credit card transaction records, including detailed information on transaction amounts, merchant details, geolocation, device usage, and fraud labels. It is designed for training and evaluating fraud detection models, supporting the identification of both typical and anomalous transaction patterns. The dataset is ideal for fintech AI development, security analytics, and research into payment fraud behaviors.

  • opened 10 times
  • last updated 12 Jul 2025
  • by GoMask
The brief that made it

Training and benchmarking credit card fraud detection models

Sample rows

preview · 8 of 200 rows · all 21 columns
transaction_idstringapproval_statusstringtransaction_amountfloatis_internationalbooleanmerchant_categorystringtransaction_datetimedatetimecard_numberstringcardholder_idstringmerchant_idstringmerchant_namestringcurrency_codestringtransaction_typestringentry_modestringdevice_idstringlocation_citystringlocation_statestringlocation_countrystringis_onlinebooleanis_fraudbooleanfraud_typestringresponse_codestring
TXN000001approved32.45falsegrocery2024-05-23T14:18:45Z****8923CH001M1001QuickMartUSDpurchasechipDVC10001ChicagoILUSAfalsefalseblank00
TXN000002approved85.99falseapparel2024-06-14T19:05:32ZABCD-7382CH002M1022FashionBayUSDpurchaseswipeDVC10221San DiegoCAUSAfalsefalseblank00
TXN000003approved458.5falseelectronics2024-04-01T16:27:14Z****-5748CH003M1105ElectroZoneUSDpurchasecontactlessDVC11051DallasTXUSAfalsefalseblank00
TXN000004approved15.25falsebooks2024-06-17T09:43:24ZGHIJ-9921CH004M1204BookNestUSDpurchaseonlineWEB-20415BostonMAUSAtruefalseblank00
TXN000005approved67.98falsegrocery2024-03-29T13:19:03Z****-3821CH005M1302FarmFreshUSDpurchasechipDVC13021SeattleWAUSAfalsefalseblank00
TXN000006approved112.1falsegifts2024-04-18T17:32:17ZWXYZ-4830CH006M1401GiftWorldUSDpurchaseswipeDVC14013PhoenixAZUSAfalsefalseblank00
TXN000007approved59.76falsefuel2024-06-21T21:10:04Z****-1207CH007M1507FuelExpressUSDpurchasemanualDVC15071HoustonTXUSAfalsefalseblank00
TXN000008approved18.5falserestaurant2024-02-14T08:29:56ZLMNO-2714CH008M1606TinyCafeUSDpurchasecontactlessDVC16061San FranciscoCAUSAfalsefalseblank00

What the 200 rows show

from the 200-row sample

Declined (approval status) stands out: mean transaction_amount is 52,184, against 1,439 for the rest.

  • 15%is_international = true
  • 99.2median transaction_amount
  • 4transaction types
  • 5currency codes
  • 5entry modes
  • 6location countries
Mean transaction_amount by approval_status200 rows
040k80k1,507approved166 rows52,184declined26 rows20.8pending8 rows
transaction_amount200 rows, in bands of 20k
0951901833422231080k160ktransaction_amount →

Median 99.2, from 0.01 to 150,000.

merchant_category196 rows with a value · 4 left blank
  1. travel26
  2. grocery24
  3. financial21
  4. electronics19
  5. fuel18
  6. apparel17
  7. books17
  8. gifts15
  9. restaurant15
  10. automotive15
21 columns by typefrom the column list below
  • string 16
  • float 1
  • datetime 1
  • boolean 3

Columns

21 columns in four groups
blueprint · 21 columns
columntypedescriptionexample
Text 16 columns
transaction_idstringUnique identifier for each transactionuniqueTXN000001
card_numberstringMasked credit card number used for the transaction (e.g., last 4 digits or hashed)****8923
cardholder_idstringUnique identifier for the cardholder (can be anonymized)CH001
merchant_idstringUnique identifier for the merchant where the transaction took placeM1001
merchant_namestringName of the merchantoptionalQuickMart
merchant_categorystringCategory of the merchant (e.g., grocery, electronics, travel)11 categories · optionalgrocery
currency_codestringISO 4217 currency code for the transaction (e.g., USD, EUR)5 codesUSD
transaction_typestringType of transaction (e.g., purchase, refund, withdrawal, transfer)purchase · refund · withdrawal · transferpurchase
entry_modestringHow the card was used (e.g., chip, swipe, contactless, online, manual entry)chip · swipe · contactless · online · manual · optionalchip
device_idstringIdentifier for the device or terminal used in the transactionoptionalDVC10001
location_citystringCity where the transaction occurredoptionalChicago
location_statestringState or province where the transaction occurredoptionalIL
location_countrystringCountry where the transaction occurred6 countries · optionalUSA
fraud_typestringType of fraud detected (e.g., stolen card, account takeover, synthetic identity); null if not fraud6 types · optionalstolen_card
response_codestringAuthorization response code from the payment processoroptional00
approval_statusstringStatus of the transaction (e.g., approved, declined, pending)approved · declined · pendingapproved
Numbers 1 column
transaction_amountfloatAmount of the transaction in the local currency0.01 or more32.45
Dates and times 1 column
transaction_datetimedatetimeDate and time when the transaction occurred2024-05-23T14:18:45Z
True or false 3 columns
is_internationalbooleanIndicates if the transaction was international (true) or domestic (false)optionalfalse
is_onlinebooleanIndicates if the transaction was performed onlineoptionalfalse
is_fraudbooleanLabel indicating if the transaction is fraudulent (true) or legitimate (false)false

Use it for

  • is internation…15%30 of 198 rowsmean transaction amou…1.5kapprov…52.2kdeclin…20.8pending

    A finance dashboard

    The is_international rate, transaction_amount by approval_status and a breakdown of merchant_category. Excel, Power BI or Tableau.

  • Why do the 26 declined rows have a mean transaction_amount of 52,184?

    A root-cause class exercise

    Hand out the rows and one question. The answer is in the data, not in the brief.

  • A software demo

    Believable transactions with transaction_datetime, card_number and cardholder_id to fill a screen in front of a buyer.

Not quite right?

Make it yours.

Same 21 columns, your size and your rules. See 20 rows before you pay.

Preview 20 rows free

1,000 rows: $1.99 · 10,000: $12.99One-time. No subscription. All prices

This dataset200 rows21 columns
Yours1,000 rows21 columnslocation_city: UK only

blueprint · credit-card-fraud-patterns

Behind this dataset

Same schema. As many rows as you need.

These 200 rows came out of a blueprint — 21 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
  • Fraudulent events <3% of total
  • Transaction times vary realistically
  • Amounts follow normal and outlier distributions
  • Cardholder profiles are anonymized
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-patterns

More in Finance

Browse all
Also in FinanceFinancial Transaction Fraud PatternsPersonal Finance Budgeting RecordsBank Transaction Categorization SampleAll 1,954 datasets
In collectionsFraud Detection Datasets

What should your data show?

Preview 20 rows free
No signup. No card.