Data Products

Synthetic fraud time-series dataset generated by the BankSim payments simulator. This dataset contains 180 transactions for each one of the 4112 customers, and fraudulent transactions are flagged.

Dataset for predicting customer churn for a banking institution. Accurately predicting churn and being proactive to avoid it will lead to higher customer retention rates. This dataset contains users from France, Germany and Spain.

This credit scoring dataset contains historical behavioural data, where each row represents a person who took a credit line. The objective to assess the risk of a credit product by predicting as accurately as possible the probability of default.

This housing prices dataset includes information on all registered property sales in England and Wales that are sold for full market value. Address details have been truncated to the town/city level.

This dataset contains information on default payments, demographic factors, credit data, history of payment, and bill statements of credit card clients in Taiwan from April 2005 to September 2005.

Dataset related to direct marketing campaigns of a Portuguese banking institution, based on phone calls.