Real-Time Fraudulent Transaction Alerts

This dataset provides comprehensive, real-time records of suspicious financial transactions flagged for potential fraud in digital banking platforms. It includes detailed transaction data, risk scores, fraud patterns, investigation outcomes, and contextual information such as device, channel, and location. Ideal for developing and benchmarking fraud detection models, auditing risk management processes, and supporting regulatory compliance.

  • 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 22 columns
alert_idstringalert_statusstringfraud_scorefloatis_fraudulentbooleanmerchant_categorystringtransaction_idstringaccount_idstringcustomer_idstringtransaction_datetimedatetimealert_datetimedatetimetransaction_amountfloattransaction_currencystringtransaction_typestringmerchant_namestringtransaction_location_citystringtransaction_location_statestringtransaction_location_countrystringdevice_idstringchannelstringfraud_patternstringinvestigator_idstringinvestigation_notesstring
ALERT00001pending0.23falseretailTXN001ACC10001CUST0012024-03-21T13:12:15Z2024-03-21T13:13:02Z87.54USDpurchaseTargetNew YorkNYUSWEB-1423552webvelocityblankblank
ALERT00002pending0.36falsecoffee_shopTXN002ACC10002CUST0022024-03-19T09:22:40Z2024-03-19T09:23:44Z153.88USDpaymentStarbucksSan FranciscoCAUSMOB-98342mobilegeo_anomalyblankblank
ALERT00003pending0.19falsee-commerceTXN003ACC10003CUST0032024-03-22T21:00:52Z2024-03-22T21:01:11Z31.7EURpurchaseZalandoBerlinBEDEWEB-443211weblocation_mismatchblankblank
ALERT00004pending0.38falseelectronicsTXN004ACC10004CUST0042024-03-18T12:48:22Z2024-03-18T12:49:06Z1299.98USDpurchaseBest BuyChicagoILUSWEB-839201webvelocityblankblank
ALERT00005pending0.13falsebooksTXN005ACC10005CUST0052024-03-17T17:28:45Z2024-03-17T17:29:41Z235.4CADrefundChaptersTorontoONCAWEB-934820webrefund_abuseblankblank
ALERT00006investigated0.54falsebankingTXN006ACC10006CUST0062024-03-17T21:55:33Z2024-03-17T21:55:48Z22000USDtransferblankNew YorkNYUSWEB-555001webunusual_amountANALYST01Reviewed large transfer; no fraud detected.
ALERT00007investigated0.42falsebankingTXN007ACC10007CUST0072024-03-16T14:03:02Z2024-03-16T14:03:45Z15500GBPdepositblankLondonENGGBBRANCH-30251branchlarge_crypto_transferANALYST02Deposit reviewed, origin verified.
ALERT00008confirmed0.99trueinvestmentTXN008ACC10008CUST0082024-03-21T16:05:29Z2024-03-21T16:06:10Z9800000USDtransferblankNew YorkNYUSWEB-212001webunusual_amountANALYST03Confirmed: unauthorized high-value transfer.

What the 200 rows show

from the 200-row sample

Confirmed (alert status) stands out: 22 of its 22 rows have is_fraudulent = true, against 3 of 178 for the rest.

  • 13%is_fraudulent = true
  • 0.24median fraud_score
  • 6channels
  • 7transaction types
  • 10transaction currencies
  • 11fraud patterns
Is fraudulent rate by alert_statusis_fraudulent = true
0%50%100%0%pending0 of 1087%investig…3 of 45100%confirmed22 of 220%dismissed0 of 25

Confirmed (alert status)'s mean fraud_score is 0.95, against 0.21 for pending, 0.56 for investigated and 0.03 for dismissed.

fraud_score200 rows, in bands of 0.1
030603051352412107192100.51fraud_score →

Median 0.24, from 0.0 to 1.0.

merchant_category178 rows with a value · 22 left blank
  1. banking53
  2. groceries30
  3. e-commerce20
  4. retail17
  5. electronics13
  6. books13
  7. crypto9
  8. coffee_shop8
  9. investment7
  10. transport4
22 columns by typefrom the column list below
  • string 17
  • float 2
  • datetime 2
  • boolean 1

Columns

22 columns in four groups
blueprint · 22 columns
columntypedescriptionexample
Text 17 columns
alert_idstringUnique identifier for each fraud alert event.uniqueALERT00001
transaction_idstringUnique identifier for the underlying financial transaction.TXN001
account_idstringUnique identifier for the customer account involved in the transaction.ACC10001
customer_idstringUnique identifier for the customer associated with the account.CUST001
transaction_currencystringISO 4217 currency code for the transaction (e.g., USD, EUR).10 currenciesUSD
transaction_typestringType of transaction (e.g., withdrawal, deposit, transfer, payment).7 valuespurchase
merchant_namestringName of the merchant or counterparty involved in the transaction.optionalTarget
merchant_categorystringCategory code or description for the merchant (e.g., groceries, electronics).11 categories · optionalretail
transaction_location_citystringCity where the transaction was initiated.optionalNew York
transaction_location_statestringState or region where the transaction was initiated.optionalNY
transaction_location_countrystringCountry where the transaction was initiated.optionalUS
device_idstringIdentifier for the device used to initiate the transaction.optionalWEB-1423552
channelstringChannel through which the transaction was made (e.g., mobile, web, ATM, branch).6 valuesweb
fraud_patternstringShort code or description of the suspicious pattern detected (e.g., 'velocity', 'geolocation', 'unusual_amount').11 patternsvelocity
alert_statusstringCurrent status of the alert (e.g., pending, investigated, confirmed, dismissed).pending · investigated · confirmed · dismissedpending
investigator_idstringIdentifier for the fraud analyst or system that reviewed the alert.optionalANALYST01
investigation_notesstringFree-text notes from the investigation or review process.optionalRoutine system test.
Numbers 2 columns
transaction_amountfloatMonetary value of the transaction.0 or more87.54
fraud_scorefloatRisk score assigned to the transaction (0-1, higher means more likely fraudulent).0 to 10.23
Dates and times 2 columns
transaction_datetimedatetimeTimestamp when the transaction occurred.2024-03-21T13:12:15Z
alert_datetimedatetimeTimestamp when the fraud alert was generated.2024-03-21T13:13:02Z
True or false 1 column
is_fraudulentbooleanIndicates whether the transaction was confirmed as fraudulent.false

Use it for

  • is fraudulent13%25 of 200 rowsmean fraud score by a…0.21pend…0.56inve…0.95conf…0.03dism…

    A finance dashboard

    The is_fraudulent rate, fraud_score by alert_status and a breakdown of merchant_category. Excel, Power BI or Tableau.

  • Why do 25 of 200 rows have is_fraudulent = 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 alerts with transaction_id, account_id and customer_id to fill a screen in front of a buyer.

Not quite right?

Make it yours.

Same 22 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 rows22 columns
Yours1,000 rows22 columnstransaction_location_city: UK only

blueprint · real-time-fraudulent-transaction-alerts

Behind this dataset

Same schema. As many rows as you need.

These 200 rows came out of a blueprint — 22 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 row is a flagged transaction event.
  • Includes user, location, device, and time data.
  • Fraud label based on transaction rules.
  • Supports multi-factor anomaly scoring.
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
real-time-fraudulent-transaction-alerts

More in Finance

Browse all
Also in FinanceCard Fraud PatternsTransaction Categorization DatasetCredit Card Fraud DetectionAll 1,967 datasets

What should your data show?

Preview 20 rows free
No signup. No card.