5 datasets found

The Home Credit Default Risk dataset, used to test the fairness of algorithms.

The German credit risk dataset contains 1,000 samples with 9 attributes. The goal is to predict whether a client is highly risky, and the sensitive attribute in this dataset is...

The dataset used in the paper for numeric data generation and classification.

The dataset used in this paper is the German dataset, which is a real-world UCI Machine Learning dataset extracted from a German bank for default prediction.

Each node is a client in a German bank, while each edge between any two clients represents that they bear similar credit accounts. Here the gender of bank clients is considered...