High-Cardinality Categorical Attributes and Credit Card Fraud Detection

Credit card transactions may contain some categorical attributes with large domains, involving up to hundreds of possible values, also known as high-cardinality attributes. The inclusion of such attributes makes analysis harder, due to results with poorer generalization and higher resource usage. A common practice is, therefore, to ignore such attributes, removing them, albeit wasting the information they provided. Contrariwise, this paper reports our findings on the positive impacts of using high-cardinality attributes on credit card fraud detection. Thus, we present a new algorithm for domain reduction that preserves the fraud-detection capabilities. Experiments applying a deep feedforward neural network on real datasets from a major Brazilian financial institution have shown that, when measured by the F-1 metric, the inclusion of such attributes does improve fraud-detection quality. As a main contribution, this proposed algorithm was able to reduce attribute cardinality, improving the training times of a model while preserving its predictive capabilities.