Banking Transaction Sequence Patterns

This dataset provides detailed, synthetic banking transaction records across customer accounts, including transaction types, amounts, channels, geolocation, and fraud indicators. Designed for advanced sequence modeling, fraud detection, and behavioral segmentation, it enables deep analysis of financial activity patterns and risk assessment. The rich set of attributes supports both supervised and unsupervised machine learning applications in financial analytics.

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

Fraud detection and anomaly detection in banking transactions

Sample rows

preview · 8 of 200 rows · all 17 columns
transaction_idstringchannelstringtransaction_amountfloatis_fraudulentbooleanmerchant_categorystringcustomer_idstringaccount_idstringtransaction_datetimedatetimetransaction_typestringcurrencystringmerchant_idstringtransaction_descriptionstringbalance_after_transactionfloatdevice_idstringtransaction_location_latitudefloattransaction_location_longitudefloatrelated_transaction_idstring
TXN100001online2450falseblankCUS1001ACC200012024-05-01T09:15:23ZdepositUSDblankSalary deposit for May12450DEV100140.7128-74.006blank
TXN100002mobile-120.75falsegroceriesCUS1002ACC200022024-05-01T10:05:12ZpaymentUSDMER9001Payment at FreshMart3879.25DEV100234.0522-118.2437blank
TXN100003branch-12falsebank_feesCUS1001ACC200012024-05-01T11:17:41ZfeeUSDMER9002Monthly maintenance fee12438blank40.713-74.0059blank
TXN100004branch1500falseblankCUS1003ACC200032024-05-01T12:00:00ZdepositEURblankMonthly pension deposit3500blank48.85662.3522blank
TXN100005atm-300falseblankCUS1004ACC200042024-05-01T13:21:44ZwithdrawalUSDblankATM cash withdrawal2200DEV100441.8781-87.6298blank
TXN100006mobile1800falseblankCUS1002ACC200022024-05-01T14:05:30ZdepositUSDblankPaycheck deposit5679.25DEV100234.0524-118.244blank
TXN100007online-60falseutilitiesCUS1003ACC200032024-05-01T15:30:00ZpaymentEURMER9003Electricity bill payment3440DEV100348.8572.353blank
TXN100008mobile350falseblankCUS1005ACC200052024-05-02T08:00:00ZdepositUSDblankAllowance deposit850DEV100540.7306-73.9352blank

What the 200 rows show

from the 200-row sample
  • 7%is_fraudulent = true
  • -7.8median transaction_amount
  • 6currencies
  • 7transaction types
  • 1,600median balance_after_transaction
channel200 rows by value
0408076online38%27atm14%43branch22%52mobile26%2other1%
transaction_amount200 rows, in bands of 200M
0601203000114800003-1B01Btransaction_amount →

Median -7.8, from -1,000,000,000 to 1,000,000,000.

merchant_category83 rows with a value · 117 left blank
  1. bank_fees24
  2. utilities10
  3. groceries9
  4. entertainment7
  5. food6
  6. electronics6
  7. travel5
  8. atm_fees3
  9. education3
  10. auto3
17 columns by typefrom the column list below
  • string 11
  • float 4
  • datetime 1
  • boolean 1

Columns

17 columns in four groups
blueprint · 17 columns
columntypedescriptionexample
Text 11 columns
transaction_idstringUnique identifier for each transaction.uniqueTXN100001
customer_idstringUnique identifier for the customer account associated with the transaction.CUS1001
account_idstringUnique identifier for the specific bank account involved in the transaction.ACC20001
transaction_typestringType of transaction, such as deposit, withdrawal, transfer, payment, etc.7 valuesdeposit
currencystringISO 4217 currency code for the transaction (e.g., USD, EUR).6 currenciesUSD
merchant_idstringUnique identifier for the merchant or counterparty involved in the transaction, if applicable.optionalMER9001
merchant_categorystringCategory of the merchant or transaction (e.g., groceries, utilities, entertainment).optionalgroceries
transaction_descriptionstringFree-text description or memo associated with the transaction.optionalSalary deposit for May
device_idstringIdentifier for the device used to initiate the transaction, if available.optionalDEV1001
channelstringChannel through which the transaction was made (e.g., online, ATM, branch, mobile).6 values · optionalonline
related_transaction_idstringIdentifier of a related transaction (e.g., for transfers or reversals), if applicable.optionalTXN100010
Numbers 4 columns
transaction_amountfloatMonetary amount of the transaction. Positive for credits, negative for debits.2450
balance_after_transactionfloatAccount balance immediately after the transaction is processed.optional12450
transaction_location_latitudefloatLatitude of the location where the transaction was initiated, if available.-90 to 90 · optional40.7128
transaction_location_longitudefloatLongitude of the location where the transaction was initiated, if available.-180 to 180 · optional-74.006
Dates and times 1 column
transaction_datetimedatetimeDate and time when the transaction occurred.2024-05-01T09:15:23Z
True or false 1 column
is_fraudulentbooleanFlag indicating if the transaction is known or suspected to be fraudulent.optionalfalse

Use it for

  • is fraudulent7%13 of 200 rowsrows by channel76onli…27atm43bran…52mobi…

    A finance dashboard

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

  • Why do 13 of 200 rows have is_fraudulent = true?

    A class exercise

    Hand out the rows and one question. Everyone works from the same 200 rows.

  • A software demo

    Believable transactions with customer_id, account_id and transaction_datetime to fill a screen in front of a buyer.

Not quite right?

Make it yours.

Same 17 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 rows17 columns
Yours1,000 rows17 columnstransaction_location_latitude: UK only

blueprint · banking-transaction-sequence-patterns

Behind this dataset

Same schema. As many rows as you need.

These 200 rows came out of a blueprint — 17 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 account assigned a unique ID
  • Transactions ordered by time
  • Include deposits, withdrawals, payments
  • Flag possible suspicious patterns
  • Account demographics 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
banking-transaction-sequence-patterns

More in Finance

Browse all
Also in FinanceFinancial Transaction Fraud ScoresCredit Card Fraud DetectionBanking Transaction Categorization DatasetAll 1,966 datasets

What should your data show?

Preview 20 rows free
No signup. No card.