This dataset contains a set of banking transactions and other data from a Czech bank.
The data has been pseudonymized and slightly anonymized. It was originally used for a machine learning competition.
It has seven different tables. The transactions table for example contains over 1.2M transactions across 5300 customers. The unique user identifier (uid) represents one customer (noting that some customers share an account).
The data can be explored via SQL client at https://db001.gda-score.org/. Server ‘PostgreSQL’, database ‘raw_banking’, tables ‘accounts’, ‘cards’, ‘clients’, ‘disp’, ‘loans’, ‘orders’, ‘transactions’.