Fraud Dataset Benchmark and Applications

TL;DR

This paper introduces the Fraud Dataset Benchmark (FDB), a comprehensive collection of datasets and tools designed to advance research and development in fraud detection by addressing its unique challenges.

Contribution

The paper presents FDB, a standardized benchmark with datasets and a library, tailored for diverse fraud detection tasks and challenges, facilitating consistent evaluation and innovation.

Findings

Demonstrated applications include feature engineering and algorithm comparison.

Showcased methods for class imbalance and label noise handling.

Provided a unified platform for fraud detection research.

Abstract

Standardized datasets and benchmarks have spurred innovations in computer vision, natural language processing, multi-modal and tabular settings. We note that, as compared to other well researched fields, fraud detection has unique challenges: high-class imbalance, diverse feature types, frequently changing fraud patterns, and adversarial nature of the problem. Due to these, the modeling approaches evaluated on datasets from other research fields may not work well for the fraud detection. In this paper, we introduce Fraud Dataset Benchmark (FDB), a compilation of publicly available datasets catered to fraud detection FDB comprises variety of fraud related tasks, ranging from identifying fraudulent card-not-present transactions, detecting bot attacks, classifying malicious URLs, estimating risk of loan default to content moderation. The Python based library for FDB provides a consistent API for data loading with standardized training and testing splits. We demonstrate several applications of FDB that are of broad interest for fraud detection, including feature engineering, comparison of supervised learning algorithms, label noise removal, class-imbalance treatment and semi-supervised learning. We hope that FDB provides a common playground for researchers and practitioners in the fraud detection domain to develop robust and customized machine learning techniques targeting various fraud use cases.