Differentiable Inductive Logic Programming for Fraud Detection

TL;DR

This paper explores the use of Differentiable Inductive Logic Programming (DILP) for fraud detection, emphasizing explainability and demonstrating its potential with data curation despite scalability challenges.

Contribution

It investigates DILP's applicability to fraud detection, highlighting data preparation techniques and identifying scenarios where DILP outperforms traditional methods.

Findings

DILP achieves comparable results to decision trees and deep symbolic classifiers.

Data curation improves DILP's applicability and performance.

DILP shows promise in recursive rule learning for fraud detection.

Abstract

Current trends in Machine Learning prefer explainability even when it comes at the cost of performance. Therefore, explainable AI methods are particularly important in the field of Fraud Detection. This work investigates the applicability of Differentiable Inductive Logic Programming (DILP) as an explainable AI approach to Fraud Detection. Although the scalability of DILP is a well-known issue, we show that with some data curation such as cleaning and adjusting the tabular and numerical data to the expected format of background facts statements, it becomes much more applicable. While in processing it does not provide any significant advantage on rather more traditional methods such as Decision Trees, or more recent ones like Deep Symbolic Classification, it still gives comparable results. We showcase its limitations and points to improve, as well as potential use cases where it can be much more useful compared to traditional methods, such as recursive rule learning.