Fraudulent Transaction Identification

This dataset provides detailed records of financial transactions, enriched with fraud detection indicators, device and location metadata, and merchant information. It is designed to help financial institutions identify and analyze fraudulent activities, supporting both real-time monitoring and historical pattern analysis for risk mitigation and compliance.

  • last updated 20 Aug 2025
  • by GoMask
The brief that made it

Automated fraud detection and prevention in banking systems

Sample rows

preview · 8 of 200 rows · all 23 columns
transaction_idstringtransaction_typestringfraud_scorefloatis_fraudbooleanfraud_typestringaccount_idstringcustomer_idstringtransaction_datetimedatetimetransaction_amountfloatcurrencystringmerchant_idstringmerchant_namestringlocation_streetstringlocation_citystringlocation_statestringlocation_postal_codestringlocation_countrystringdevice_idstringdevice_typestringip_addressstringdetection_methodstringreported_datetimedatetimenotesstring
TXN00001purchaseblankfalseblankACC1001CUST20012024-06-01T09:20:15Z87.23USDMRC5001Amazon US123 Market StSan FranciscoCA94105USDEV0011mobile192.168.1.15blankblankOnline purchase - electronics
TXN00002transferblankfalseblankACC1002CUST20022024-06-03T13:45:00Z1500USDblankblank88 Pine StNew YorkNY10005USDEV0022desktop172.16.0.20blankblankInter-account transfer
TXN00003withdrawalblankfalseblankACC1003CUST20032024-06-04T17:32:41Z25USDblankblank645 Main StDenverCO80203USDEV0033ATM10.0.0.9blankblankATM cash withdrawal
TXN00004purchaseblankfalseblankACC1004CUST20042024-06-04T19:18:20Z52.44CADMRC5002Starbucks CA220 Yonge StTorontoONM5B2H1CADEV0044mobile203.0.113.14blankblankCoffee shop purchase
TXN00005depositblankfalseblankACC1001CUST20012024-06-05T08:24:36Z3000USDblankblank456 7th AveSeattleWA98101USDEV0012ATM192.168.2.22blankblankATM cash deposit
TXN00006refundblankfalseblankACC1005CUST20052024-06-05T09:14:02Z0GBPMRC5003Tesco UK18 Oxford StLondonLNDW1D1ANGBDEV0055desktop94.21.163.44blankblankRefunded grocery purchase
TXN00007paymentblankfalseblankACC1006CUST20062024-06-06T11:57:00Z105.67EURMRC5004Iberdrola ES14 Gran ViaMadridMD28013ESDEV0066desktop83.47.101.88blankblankUtility bill payment
TXN00008purchaseblankfalseblankACC1007CUST20072024-06-07T15:41:20Z12.96AUDMRC5005Coles AU67 Collins StMelbourneVIC3000AUDEV0077mobile203.1.168.108blankblankGrocery shopping

What the 200 rows show

from the 200-row sample

Transfer (transaction type) stands out: 9 of its 22 rows have is_fraud = true, against 14 of 178 for the rest.

  • 12%is_fraud = true
  • 0.96median fraud_score
  • 5device types
  • 8currencies
  • 11location countries
  • 34location states
Is fraud rate by transaction_typeis_fraud = true
0%50%100%39%with…7 of …29%depo…7 of …41%tran…9 of …0%paym…0 of …0%refu…0 of 80%purc…0 of …0%other0 of …
fraud_score23 rows, in bands of 0.02
03611021234450.80.91fraud_score →

Median 0.96, from 0.80 to 1.0.

fraud_type23 rows with a value · 177 left blank
  1. money laundering13
  2. card theft4
  3. account takeover3
  4. identity theft2
  5. phishing1
23 columns by typefrom the column list below
  • string 18
  • float 2
  • datetime 2
  • boolean 1

Columns

23 columns in four groups
blueprint · 23 columns
columntypedescriptionexample
Text 18 columns
transaction_idstringUnique identifier for each transactionuniqueTXN00001
account_idstringUnique identifier for the account involved in the transactionACC1001
customer_idstringUnique identifier for the customer associated with the accountCUST2001
currencystringCurrency code used for the transaction (ISO 4217 format)8 currenciesUSD
transaction_typestringType of transaction (e.g., withdrawal, deposit, transfer, payment)7 valuespurchase
merchant_idstringUnique identifier for the merchant or payee (if applicable)optionalMRC5001
merchant_namestringName of the merchant or payee (if applicable)optionalAmazon US
location_streetstringStreet address where the transaction occurred (if available)optional123 Market St
location_citystringCity where the transaction occurred (if available)optionalSan Francisco
location_statestringState or province where the transaction occurred (if available)optionalCA
location_postal_codestringPostal code for the transaction location (if available)optional94105
location_countrystringCountry code for the transaction location (ISO 3166-1 alpha-2)11 countries · optionalUS
device_idstringUnique identifier for the device used to perform the transactionoptionalDEV0011
device_typestringType of device used (e.g., mobile, desktop, ATM, POS)6 values · optionalmobile
ip_addressstringIP address from which the transaction was initiatedoptional192.168.1.15
fraud_typestringType of fraud detected (e.g., card theft, account takeover, phishing)6 values · optionalaccount takeover
detection_methodstringMethod or algorithm used to detect fraud (e.g., rule-based, ML model)7 methods · optionalML anomaly model
notesstringAdditional notes or comments about the transaction or investigationoptionalInter-account transfer
Numbers 2 columns
transaction_amountfloatMonetary value of the transaction0 or more87.23
fraud_scorefloatFraud risk score assigned to the transaction (0.0-1.0, higher means more likely fraud)0 to 1 · optional0.97
Dates and times 2 columns
transaction_datetimedatetimeDate and time when the transaction occurred2024-06-01T09:20:15Z
reported_datetimedatetimeDate and time when the fraud was reported or confirmedoptional2024-06-08T20:01:00Z
True or false 1 column
is_fraudbooleanFlag indicating whether the transaction is identified as fraudulentfalse

Use it for

  • is fraud12%23 of 200 rowsis fraud by transacti…39%with…29%depo…41%tran…0%paym…

    A finance dashboard

    The is_fraud rate, fraud_score by transaction_type and a breakdown of fraud_type. Excel, Power BI or Tableau.

  • Why do 23 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 account_id, customer_id and transaction_datetime to fill a screen in front of a buyer.

Not quite right?

Make it yours.

Same 23 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 rows23 columns
Yours1,000 rows23 columnslocation_street: UK only

blueprint · fraudulent-transaction-identification

Behind this dataset

Same schema. As many rows as you need.

These 200 rows came out of a blueprint — 23 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
  • Flag transactions exceeding typical thresholds
  • Label known fraudulent cases
  • Include transaction location and device info
  • Exclude manually reversed transactions
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
fraudulent-transaction-identification

More in Finance

Browse all
Also in FinanceFinancial Transaction Fraud ScoresLoan Default Prediction DatasetBank Transaction Categorization SampleAll 1,966 datasets

What should your data show?

Preview 20 rows free
No signup. No card.