Datadory notebook

Can I use the IEEE-CIS Fraud Detection dataset commercially?

1,744 datasets. Pick your catch. Every guide here is built on what the catalog can actually prove.

1,744 datasets. Pick your catch.

What are you actually downloading when you accept those rules?

The bundle is roughly 1.4 GB of CSVs: train_transaction.csv at ~683 MB and test_transaction.csv at ~613 MB, joined by a smaller pair of identity files (~26.5 MB and ~25.8 MB). The transaction table holds 590,540 labeled e-commerce payment rows across 394 features, and joins on TransactionID to a 144,233-row device and identity table, so each payment can be enriched with device-fingerprinting and identity attributes.

Where to go next

Two adjacent deep dives cover the same files from other angles: the Kaggle – IEEE-CIS Fraud Detection – 590K+ Transaction and Identity Tables (Vesta) dataset page documents the 394-feature schema and file sizes in detail, while Kaggle PaySim – Synthetic Mobile Money Transactions (1M+ rows) shows what a commercial delivery terms-SA 4.0 alternative buys you for mobile-money prototyping.

Pick up where this leaves off

Every one of these ships with sample rows before you commit to anything.

Transaction & Payment Processing Services Global e-commerce transactions with countries masked as codes

IEEE-CIS Fraud Detection – Vesta Transaction & Identity Tables

Transaction & Payment Processing Services India (domestic financial transactions

Reserve Bank of India - Payment System Indicators (Monthly Volume and Value)

Transaction & Payment Processing Services ~170 economies worldwide, plus aggregates

World Bank DataBank – Global Financial Inclusion (Global Findex Query Interface)

Transaction & Payment Processing Services United Kingdom - domestic clearing across the four interbank…

UK Finance / Pay.UK – UK Payment Markets and Payments Statistics

Transaction & Payment Processing Services European cardholders

Credit Card Fraud Detection (ULB) – 284,807 European Card Transactions

Time · Amount · Class

Transaction & Payment Processing Services None stated - synthetic data scaled from an aggregated sample…

Kaggle PaySim - Synthetic Mobile Money Transactions (1M+ Rows)

step · type · amount …+8 more

Want rows instead of a pitch? Name the datasets.

API, files, or your warehouse. Daily, weekly, or hourly.

Get a sample

Questions worth asking

Can I use the IEEE-CIS Fraud Detection dataset commercially?

Probably not without permission. The Vesta Corporation data behind the competition is accessible on demand, but Kaggle competition rules restrict use to the competition and research context and prohibit redistribution outside Kaggle. Verify the current rules covering the 590,540-row table before any commercial reuse.

Can I redistribute the IEEE-CIS dataset in my own product?

No. Its terms prohibit redistribution outside Kaggle without permission, so re-hosting the 1.4 GB of CSVs or embedding them in a downloadable product requires clearance from Vesta Corporation regardless of whether your use case charges money.