Explainable Machine Learning for Fraud Detection
Machine Learning
2021-05-14 v1 Artificial Intelligence
Abstract
The application of machine learning to support the processing of large datasets holds promise in many industries, including financial services. However, practical issues for the full adoption of machine learning remain with the focus being on understanding and being able to explain the decisions and predictions made by complex models. In this paper, we explore explainability methods in the domain of real-time fraud detection by investigating the selection of appropriate background datasets and runtime trade-offs on both supervised and unsupervised models.
Cite
@article{arxiv.2105.06314,
title = {Explainable Machine Learning for Fraud Detection},
author = {Ismini Psychoula and Andreas Gutmann and Pradip Mainali and S. H. Lee and Paul Dunphy and Fabien A. P. Petitcolas},
journal= {arXiv preprint arXiv:2105.06314},
year = {2021}
}
Comments
To be published in IEEE Computer Special Issue on Explainable AI and Machine Learning, 12 pages, 7 figures