Financial Transaction Fraud Detection

This dataset provides detailed, labeled records of financial transactions, including transaction amounts, types, geolocation, merchant details, and fraud indicators. Designed for robust fraud detection model development and benchmarking, it supports advanced analytics and machine learning in banking and payment processing. The inclusion of comprehensive transaction attributes and fraud labels makes it ideal for supervised learning and anomaly detection research.

  • opened 11 times
  • last updated 12 Jul 2025
  • by GoMask
The brief that made it

Training and benchmarking fraud detection machine learning models

Sample rows

preview · 8 of 200 rows · all 21 columns
transaction_idstringentry_methodstringtransaction_amountfloatis_internationalbooleanmerchant_categorystringaccount_idstringtransaction_datetimedatetimecurrencystringmerchant_idstringtransaction_typestringdevice_idstringlocation_latitudefloatlocation_longitudefloatbilling_street_addressstringbilling_citystringbilling_statestringbilling_postal_codestringbilling_countrystringis_fraudbooleanfraud_label_sourcestringadditional_notesstring
TXN000001chip89.45falsegroceryACC100012021-12-24T19:22:15ZUSDMCT1245purchaseDVUS234134.0522-118.2437125 Market StLos AngelesCA90017USfalseblankEvening grocery run before Christmas.
TXN000002contactless157.2falserestaurantACC100022022-02-14T13:28:52ZGBPMCT3182purchaseDVUK882151.5074-0.127822 Regent StLondonENGSW1Y4PEGBfalseblankValentine’s dinner at West End.
TXN000003swipe29.99falsepharmacyACC100032023-10-01T08:14:07ZUSDMCT9051purchaseDVUS778240.7128-74.00677 BroadwayNew YorkNY10007USfalseblankPharmacy purchase: vitamins and essentials.
TXN000004chip74.5falseclothingACC100042022-07-04T15:45:30ZUSDMCT5612purchaseDVUS983132.7767-96.797140 Main StDallasTX75201USfalseblankFourth of July sale at mall.
TXN000005manual1225.67trueelectronicsACC100052022-12-31T23:54:52ZEURMCT8320purchaseDVFR390148.85662.352251 Rue de RivoliParisIDF75004FRtrueautomated_modelHigh-value New Year's Eve electronics purchase flagged.
TXN000006contactless15.25falsefitnessACC100062021-11-29T16:05:12ZUSDMCT2045paymentDVUS521637.7749-122.4194320 Van Ness AveSan FranciscoCA94102USfalseblankMonthly gym membership fee.
TXN000007other0.01falsetestACC100072023-05-12T19:11:36ZUSDblankotherDVTEST00500N/AN/AN/A00000USfalseblankTest microtransaction, QA environment.
TXN000008swipe998.4truetravelACC100082022-06-15T13:30:29ZJPYMCT3346purchaseDVJP112335.6895139.69172-11-3 ShibuyaTokyoTKY150-0002JPfalseblankLocal train ticket purchase.

What the 200 rows show

from the 200-row sample

Manual (entry method) stands out: 23 of its 27 rows have is_international = true, against 23 of 159 for the rest.

  • 23%is_international = true
  • 54.6median transaction_amount
  • 3fraud label sources
  • 7transaction types
  • 10currencies
  • 12billing countries
Is international rate by entry_methodis_international = true
0%50%100%17%chip13 of…8%swipe2 of …25%onli…3 of …43%mobi…3 of 70%cont…0 of …85%manu…23 of…17%other2 of …
transaction_amount200 rows, in bands of 1M
010020019610001000205M10Mtransaction_amount →

Median 54.6, from 0.0 to 10,000,000.

merchant_category186 rows with a value · 14 left blank
  1. grocery29
  2. electronics21
  3. restaurant19
  4. pharmacy18
  5. clothing18
  6. fitness16
  7. travel14
  8. books12
  9. test9
  10. real_estate8
21 columns by typefrom the column list below
  • string 15
  • float 3
  • datetime 1
  • boolean 2

Columns

21 columns in four groups
blueprint · 21 columns
columntypedescriptionexample
Text 15 columns
transaction_idstringUnique identifier for each financial transactionuniqueTXN000001
account_idstringUnique identifier for the account involved in the transactionACC10001
currencystringISO 4217 currency code for the transaction (e.g., USD, EUR)10 currenciesUSD
merchant_idstringUnique identifier for the merchant or payeeoptionalMCT1245
merchant_categorystringCategory or type of merchant (e.g., grocery, electronics, travel)optionalgrocery
transaction_typestringType of transaction (e.g., purchase, withdrawal, transfer, payment)7 valuespurchase
device_idstringIdentifier for the device used to initiate the transactionoptionalDVUS2341
entry_methodstringHow the transaction was initiated (e.g., chip, swipe, online, mobile, contactless)7 values · optionalchip
billing_street_addressstringStreet address associated with the billing accountoptional125 Market St
billing_citystringCity of the billing addressoptionalLos Angeles
billing_statestringState or province of the billing addressoptionalCA
billing_postal_codestringPostal or ZIP code of the billing addressoptional90017
billing_countrystringCountry of the billing address (ISO 3166-1 alpha-2 code)12 countries · optionalUS
fraud_label_sourcestringSource or method used to label the transaction as fraud (e.g., manual review, automated model, customer report)manual_review · automated_model · customer_report · other · optionalautomated_model
additional_notesstringOptional notes or comments related to the transaction or fraud investigationoptionalPrescription refill.
Numbers 3 columns
transaction_amountfloatMonetary value of the transaction0 or more89.45
location_latitudefloatLatitude coordinate of the transaction location-90 to 90 · optional34.0522
location_longitudefloatLongitude coordinate of the transaction location-180 to 180 · optional-118.2437
Dates and times 1 column
transaction_datetimedatetimeDate and time when the transaction occurred2021-12-24T19:22:15Z
True or false 2 columns
is_internationalbooleanIndicates if the transaction is international (true) or domestic (false)optionalfalse
is_fraudbooleanLabel indicating whether the transaction is fraudulent (true) or not (false)false

Use it for

  • is internation…23%46 of 200 rowsmean transaction amou…633.3chip112.0swipe62.3onli…46.8mobi…

    A finance dashboard

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

  • Why do 46 of 200 rows have is_international = true?

    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 account_id, transaction_datetime and transaction_amount 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_latitude: UK only

blueprint · financial-transaction-fraud-detection

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
  • Transactions above $10,000 flagged for review
  • Multiple transactions from new locations within 1 hour flagged
  • Account holder age must be 18+
  • Rejected transactions included with reasons
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
financial-transaction-fraud-detection

More in Finance

Browse all
Also in FinanceFraudulent Transaction IdentificationBank Customer Segmentation DatasetBank Transaction Category ClassificationAll 1,966 datasets
In collectionsFraud Detection Datasets

What should your data show?

Preview 20 rows free
No signup. No card.