Financial Transaction Fraud Labels

This dataset contains detailed records of financial transactions, including customer demographics, merchant information, device characteristics, and explicit fraud labels. It is designed for machine learning-driven fraud detection, risk analysis, and real-time alerting, enabling robust analytics and model development for financial institutions and payment processors.

  • last updated 21 Jul 2025
  • by GoMask
The brief that made it

Training and evaluating machine learning models for fraud detection

Sample rows

preview · 8 of 200 rows · all 19 columns
transaction_idstringcustomer_genderstringamountfloatis_fraudbooleancustomer_countrystringtransaction_datetimedatetimecurrencystringcustomer_idstringcustomer_ageintegermerchant_idstringmerchant_namestringmerchant_categorystringmerchant_countrystringdevice_idstringdevice_typestringdevice_osstringip_addressstringfraud_label_sourcestringfraud_report_datetimedatetime
TXN000001male156.27falseUS2024-03-15T11:14:22ZUSDCUST00000129MERCHANT001Tech OutletelectronicsUSDEV1001mobileiOS192.168.1.102blankblank
TXN000002female47.99falseGB2023-12-24T19:42:05ZGBPCUST00000233MERCHANT002Book NookbooksGBDEV1002desktopWindows51.6.163.44blankblank
TXN000003male1899.2falseDE2022-11-07T08:10:11ZEURCUST00000354MERCHANT003Elegant JewelersjewelryDEDEV1003desktopLinux88.130.11.199blankblank
TXN000004unknown0trueblank2024-01-01T00:05:48ZJPYCUST0000040MERCHANT004blanktestblankblankblankblankblankml_model2024-01-01T13:32:17Z
TXN000005female57.45falseUS2022-07-09T14:03:45ZUSDCUST00000522MERCHANT005Fresh MarketgroceryUSDEV1004mobileAndroid10.0.0.15blankblank
TXN000006male12003.3falseCA2023-05-30T23:42:12ZCADCUST00000663MERCHANT006AutoPro ServiceautomotiveCADEV1005desktopWindows24.114.98.200blankblank
TXN000007female35.99falseDE2023-02-14T17:25:13ZEURCUST00000725MERCHANT007Fine DiningrestaurantDEDEV1006tabletAndroid91.43.22.14blankblank
TXN000008male320falseUS2022-12-25T09:22:09ZUSDCUST00000844MERCHANT008TravelWiztravelUSDEV1007desktopmacOS172.16.0.111blankblank

What the 200 rows show

from the 200-row sample

Unknown (customer gender) stands out: 29 of its 30 rows have is_fraud = true, against 0 of 170 for the rest.

  • 14%is_fraud = true
  • 120.0median amount
  • 4fraud label sources
  • 5device types
  • 7device oses
  • 12currencies
Is fraud rate by customer_genderis_fraud = true
0%50%100%0%male0 of 740%female0 of 830%other0 of 1397%unknown29 of 30

Unknown (customer gender)'s mean amount is 716,477, against 3,762 for male, 8,612 for female and 28.3 for other.

amount200 rows, in bands of 500k
010020019501000000402.5M5Mamount →

Median 120.0, from 0.0 to 5,000,000.

customer_country183 rows with a value · 17 left blank
  1. US57
  2. DE17
  3. IN16
  4. CA14
  5. GB12
  6. AU12
  7. CN12
  8. SE10
  9. JP9
  10. CH9
19 columns by typefrom the column list below
  • string 14
  • integer 1
  • float 1
  • datetime 2
  • boolean 1

Columns

19 columns in four groups
blueprint · 19 columns
columntypedescriptionexample
Text 14 columns
transaction_idstringUnique identifier for each financial transactionuniqueTXN000001
currencystringISO 4217 currency code used for the transaction (e.g., USD, EUR)12 currenciesUSD
customer_idstringUnique identifier for the customer performing the transactionCUST000001
customer_genderstringGender of the customermale · female · other · unknown · optionalmale
customer_countrystringCountry of the customer at the time of transaction (ISO 3166-1 alpha-2 code)optionalUS
merchant_idstringUnique identifier for the merchant receiving the transactionMERCHANT001
merchant_namestringName of the merchantoptionalTech Outlet
merchant_categorystringCategory or type of merchant (e.g., grocery, electronics, travel)optionalelectronics
merchant_countrystringCountry where the merchant is located (ISO 3166-1 alpha-2 code)optionalUS
device_idstringUnique identifier for the device used in the transactionoptionalDEV1001
device_typestringType of device used (e.g., mobile, desktop, tablet, POS terminal)mobile · desktop · tablet · pos · other · optionalmobile
device_osstringOperating system of the device (e.g., Android, iOS, Windows, Linux)7 oses · optionaliOS
ip_addressstringIP address from which the transaction was initiated (IPv4 or IPv6)optional192.168.1.102
fraud_label_sourcestringSource of the fraud label (e.g., manual review, ML model, chargeback)manual_review · ml_model · chargeback · other · optionalml_model
Numbers 2 columns
amountfloatMonetary value of the transaction0 or more156.27
customer_ageintegerAge of the customer at the time of transaction0 to 120 · optional29
Dates and times 2 columns
transaction_datetimedatetimeDate and time when the transaction occurred2024-03-15T11:14:22Z
fraud_report_datetimedatetimeDate and time when the fraud was reported or confirmedoptional2024-01-01T13:32:17Z
True or false 1 column
is_fraudbooleanIndicates whether the transaction was labeled as fraudulent (true) or not (false)false

Use it for

  • is fraud14%29 of 200 rowsmean amount by custom…3.8kmale8.6kfema…28.3other716.5kunkn…

    A finance dashboard

    The is_fraud rate, amount by customer_gender and a breakdown of customer_country. Excel, Power BI or Tableau.

  • Why do 29 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.

  • A software demo

    Believable transactions with transaction_datetime, amount and currency to fill a screen in front of a buyer.

Not quite right?

Make it yours.

Same 19 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 rows19 columns
Yours1,000 rows19 columnscustomer_country: UK only

blueprint · financial-transaction-fraud-labels

Behind this dataset

Same schema. As many rows as you need.

These 200 rows came out of a blueprint — 19 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
  • Each transaction labeled as fraudulent or not
  • Include merchant category, amount, and timestamp
  • Simulate cross-border and high-risk patterns
  • User device and location data included
  • Customer profiles anonymized
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-labels

More in Finance

Browse all
Also in FinanceCard Fraud PatternsPersonal Finance Budgeting RecordsTransaction Categorization DatasetAll 1,966 datasets

What should your data show?

Preview 20 rows free
No signup. No card.