Microtransaction Fraud Scenarios

This dataset provides detailed synthetic microtransaction logs, capturing both legitimate and fraudulent activities with realistic attack scenarios. It includes user, transaction, device, location, and fraud scenario fields, making it ideal for developing, benchmarking, and validating fraud detection models in financial microtransaction environments.

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

Training and benchmarking fraud detection algorithms

Sample rows

preview · 8 of 201 rows · all 19 columns
transaction_idstringfraud_scenariostringprevious_fraud_count_30dintegeris_fraudbooleanlocation_countrystringuser_idstringtimestampdatetimetransaction_typestringamountfloatcurrencystringdevice_idstringip_addressstringlocation_citystringpayment_methodstringmerchant_idstringitem_idstringitem_categorystringuser_account_age_daysintegerprevious_transactions_count_24hinteger
TxA1-12cd3EFGnone0falseUSuser_10022023-10-17T14:08:55Zpurchase47.29USDdev_abc1234598.112.56.21San Franciscocredit_cardmerchant_1055item_4082electronics952
TxB2-9fGh4JKLnone0falseDEuser_10182024-03-22T11:27:34Zdeposit32450.75EURdev_xyz901283.172.120.11Berlinbank_transfermerchant_2081blankblank8201
TxC3-7kLm6OPQcard_testing3trueINuser_10502024-05-15T17:19:06Zpurchase8.99INRdev_ind345614.192.16.101Delhiprepaidmerchant_3044item_5564digital_content625
TxD4-1mbn2RSTnone0falseUSuser_10272023-07-02T19:44:10Zwithdrawal5100USDdev_usc999165.244.128.77Las Vegasbank_transfermerchant_1099blankblank14350
TxE5-3qPr8UVWnone0falseblankuser_10082022-12-09T09:03:22Ztransfer650CADblankblankblankbank_transferblankblankblank2331
TxF6-0xYz1ABCnone0falseGBuser_10042023-05-18T15:35:20Zpurchase105.5GBPdev_gb1234192.168.98.11Londonpaypalmerchant_3011item_6677apparel602
TxG7-5vBw2DEFbot_activity17trueUSuser_10592024-04-11T13:18:01Zpurchase0.01USDdev_bot99810.0.0.0Miamicredit_cardmerchant_9981item_test01test_item299
TxH8-6wCr7GHInone0falseCHuser_10322022-09-26T12:46:43Zdeposit1100CHFblankblankZurichcryptomerchant_crypto01blankcrypto_asset7250

What the 201 rows show

from the 201-row sample

None (fraud scenario) stands out: mean previous_fraud_count_30d is 0.03, against 7.2 for the rest.

  • 20%is_fraud = true
  • 0median previous_fraud_count_30d
  • 5transaction types
  • 6payment methods
  • 6item categories
  • 9currencies
Mean previous_fraud_count_30d by fraud_scenario201 rows
0487.1account_…7 rows6.6card_tes…20 rows8.0bot_acti…14 rows0.03none160 rows
previous_fraud_count_30d201 rows, in bands of 2
080160159313119212101018previous_fraud_count_30d →

Median 0, from 0 to 17.

location_country182 rows with a value · 19 left blank
  1. US75
  2. FR21
  3. IN19
  4. CH14
  5. JP12
  6. DE11
  7. AU10
  8. NL10
  9. GB9
  10. CA1
19 columns by typefrom the column list below
  • string 13
  • integer 3
  • float 1
  • datetime 1
  • boolean 1

Columns

19 columns in four groups
blueprint · 19 columns
columntypedescriptionexample
Text 13 columns
transaction_idstringUnique identifier for each microtransaction eventuniqueTxA1-12cd3EFG
user_idstringUnique identifier for the user performing the transactionuser_1002
transaction_typestringType of microtransaction (e.g., purchase, transfer, withdrawal, deposit)purchase · transfer · withdrawal · deposit · refundpurchase
currencystringISO 4217 currency code for the transaction (e.g., USD, EUR)9 currenciesUSD
device_idstringIdentifier for the device used to perform the transactionoptionaldev_abc12345
ip_addressstringIP address from which the transaction was initiatedoptional98.112.56.21
location_countrystringCountry where the transaction originated10 countries · optionalUS
location_citystringCity where the transaction originatedoptionalSan Francisco
payment_methodstringPayment method used for the transaction6 valuescredit_card
fraud_scenariostringType of fraud scenario detected (e.g., account_takeover, card_testing, bot_activity, none)5 values · optionalnone
merchant_idstringUnique identifier for the merchant or service provideroptionalmerchant_1055
item_idstringIdentifier for the item or service purchased (if applicable)optionalitem_4082
item_categorystringCategory of the item or service purchased6 categories · optionalelectronics
Numbers 4 columns
amountfloatMonetary value of the transaction0 or more47.29
user_account_age_daysintegerAge of the user's account in days at the time of transaction0 or more · optional95
previous_transactions_count_24hintegerNumber of previous transactions by the user in the past 24 hours0 or more · optional2
previous_fraud_count_30dintegerNumber of fraudulent transactions by the user in the past 30 days0 or more · optional0
Dates and times 1 column
timestampdatetimeDate and time when the transaction occurred (UTC)2023-10-17T14:08:55Z
True or false 1 column
is_fraudbooleanIndicates if the transaction is fraudulent (true) or legitimate (false)false

Use it for

  • is fraud20%41 of 201 rowsmean previous fraud c…7.1acco…6.6card…8.0bot_…0.03none

    A finance dashboard

    The is_fraud rate, previous_fraud_count_30d by fraud_scenario and a breakdown of location_country. Excel, Power BI or Tableau.

  • Why do the 160 none rows have a mean previous_fraud_count_30d of 0.03?

    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 user_id, timestamp and transaction_type 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 dataset201 rows19 columns
Yours1,000 rows19 columnsip_address: UK only

blueprint · microtransaction-fraud-scenarios

Behind this dataset

Same schema. As many rows as you need.

These 201 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
  • Transaction timestamps randomized
  • Fraud labels applied with patterns
  • Merchant categories diversified
  • Transaction values range from cents to hundreds
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
microtransaction-fraud-scenarios

More in Finance

Browse all
Also in FinanceFinancial Transaction Fraud ScenariosAccounts Receivable and Aging AnalysisDigital Wallet Transaction DatasetAll 1,967 datasets

What should your data show?

Preview 20 rows free
No signup. No card.