Financial Transaction Network Graphs

This dataset provides a comprehensive synthetic network of financial transactions, detailing entities, transaction flows, and inter-entity relationships for advanced anti-fraud and network analytics. With labeled fraud instances and relationship metadata, it enables the development and benchmarking of anomaly detection, graph learning, and risk assessment models in financial contexts.

  • last updated 22 Jul 2025
  • by GoMask
The brief that made it

Graph-based fraud detection and anomaly detection research

Sample rows

preview · 8 of 200 rows · all 17 columns
entity_idstringrelationship_typestringrelationship_strengthfloatis_fraudulentbooleanentity_countrystringentity_typestringentity_namestringentity_registration_datedatetransaction_idstringtransaction_datetimedatetimetransaction_amountfloattransaction_currencystringtransaction_typestringtransaction_statusstringsender_entity_idstringreceiver_entity_idstringfraud_label_sourcestring
E1001family0.85falseUSindividualAva Martinez2017-09-22T100012022-04-15T14:23:19Z457.83USDdepositcompletedE1001E1007blank
E1002partnership0.74falseGBbusinessNovaTech LLC2005-03-12T100022023-08-04T09:42:12Z58214.06GBPpaymentcompletedE1002E1010blank
E1003business_associate0.91falseDEfinancial_institutionGreenfield Bank1981-11-30T100032021-07-29T16:09:45Z643000.5EURdepositcompletedE1003E1002blank
E1004family0.93falseCNindividualZhihao Chen2015-06-08T100042020-12-19T05:45:21Z287.51CNYwithdrawalcompletedE1004E1012blank
E1005business_associate0.66falseDEbusinessSummit Group AG1995-01-16T100052022-10-30T11:33:57Z1084375.09EURdepositcompletedE1005E1003blank
E1006unknown0.11falseZAfinancial_institutionFirst Cape Credit Union1979-02-22T100062022-05-12T13:10:03Z22894ZARwithdrawalfailedE1006E1015blank
E1007family0.74falseINindividualPriya Singh2016-10-02T100072021-03-16T07:55:28Z7521.25INRtransfercompletedE1007E1014blank
E1008partnership0.61falseBRbusinessSunrise Holdings S.A.2000-04-29T100082022-01-14T03:12:02Z459900BRLdepositpendingE1008E1019blank

What the 200 rows show

from the 200-row sample

Unknown (relationship type) stands out: mean relationship_strength is 0.10, against 0.77 for the rest.

  • 5%is_fraudulent = true
  • 0.67median relationship_strength
  • 3entity types
  • 4transaction statuses
  • 6transaction types
  • 14transaction currencies
Mean relationship_strength by relationship_type198 rows
00.510.84owners…6 rows0.80partne…33 rows0.86family35 rows0.69busine…51 rows0.10unknown73 rows
relationship_strength198 rows, in bands of 0.1
020403338200152031392000.51relationship_strength →

Median 0.67, from 0.01 to 0.98.

entity_country200 rows · top 10 of 19 values
  1. DE21
  2. US19
  3. BR19
  4. ZA18
  5. SG18
  6. GB17
  7. CA16
  8. IN13
  9. CN12
  10. FR12
17 columns by typefrom the column list below
  • string 12
  • float 2
  • date 1
  • datetime 1
  • boolean 1

Columns

17 columns in four groups
blueprint · 17 columns
columntypedescriptionexample
Text 12 columns
entity_idstringUnique identifier for each entity (person, company, or account) in the transaction network.uniqueE1001
entity_typestringType of entity, such as individual, business, or financial institution.individual · business · financial_institutionindividual
entity_namestringName of the entity (person or organization).optionalAva Martinez
entity_countrystringCountry of registration or operation for the entity.optionalUS
transaction_idstringUnique identifier for each financial transaction.uniqueT10001
transaction_currencystringISO currency code for the transaction (e.g., USD, EUR).USD
transaction_typestringType of transaction (e.g., transfer, deposit, withdrawal, payment).6 valuesdeposit
transaction_statusstringStatus of the transaction (e.g., completed, pending, failed, reversed).completed · pending · failed · reversedcompleted
sender_entity_idstringEntity ID of the sender in the transaction (source node in the graph).E1001
receiver_entity_idstringEntity ID of the receiver in the transaction (target node in the graph).E1007
relationship_typestringType of relationship between entities (e.g., ownership, partnership, family, business_associate).5 values · optionalfamily
fraud_label_sourcestringSource or method of fraud labeling (e.g., synthetic_rule, manual_review, model_prediction).4 values · optionalmanual_review
Numbers 2 columns
transaction_amountfloatMonetary value of the transaction.0 or more457.83
relationship_strengthfloatNumeric score indicating the strength or closeness of the relationship between entities (0-1 scale).0 to 1 · optional0.85
Dates and times 2 columns
entity_registration_datedateDate when the entity was registered or created in the system.optional2017-09-22
transaction_datetimedatetimeTimestamp when the transaction occurred.2022-04-15T14:23:19Z
True or false 1 column
is_fraudulentbooleanIndicates whether the transaction is labeled as fraudulent (true) or not (false).optionalfalse

Use it for

  • is fraudulent5%9 of 200 rowsmean relationship str…0.84owne…0.80part…0.86fami…0.69busi…

    A finance dashboard

    The is_fraudulent rate, relationship_strength by relationship_type and a breakdown of entity_country. Excel, Power BI or Tableau.

  • Why do the 73 unknown rows have a mean relationship_strength of 0.10?

    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 entities with entity_type, entity_name and entity_registration_date 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 columnsentity_country: UK only

blueprint · financial-transaction-network-graphs

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
  • Simulate multi-bank, multi-currency transactions
  • Tag known fraudulent patterns
  • Include multi-hop transaction paths
  • Provide timestamps and amounts
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-network-graphs

More in Finance

Browse all
Also in FinancePayment Fraud Detection DatasetFinance Expense Categorization DatasetDigital Wallet Transaction DatasetAll 1,967 datasets

What should your data show?

Preview 20 rows free
No signup. No card.