Papers
Topics
Authors
Recent
Search
2000 character limit reached

Differentiable Inductive Logic Programming for Fraud Detection

Published 29 Oct 2024 in q-fin.RM, cs.AI, and cs.LG | (2410.21928v1)

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.

Authors (2)
Definition Search Book Streamline Icon: https://streamlinehq.com
References (21)
  1. A financial fraud detection model based on LSTM deep learning technique. Journal of Applied Security Research 15, 4 (2020), 498–516.
  2. Decision trees do not generalize to new variations. Computational Intelligence 26, 4 (2010), 449–467.
  3. Cart. Classification and regression trees (1984).
  4. Davide Chicco and Giuseppe Jurman. 2020. The advantages of the Matthews correlation coefficient (MCC) over F1 score and accuracy in binary classification evaluation. BMC genomics 21 (2020), 1–13.
  5. Logic explained networks. Artificial Intelligence 314 (2023), 103822.
  6. Neural-based classification rule learning for sequential data. In The Eleventh International Conference on Learning Representations.
  7. Wang-Zhou Dai and Stephen H Muggleton. 2020. Abductive knowledge induction from raw data. arXiv preprint arXiv:2010.03514 (2020).
  8. Symbolic data analysis as a tool for credit fraud detection. Bank i Kredyt 53, 6 (2022), 587–604.
  9. Richard Evans and Edward Grefenstette. 2018. Learning explanatory rules from noisy data. Journal of Artificial Intelligence Research 61 (2018), 1–64.
  10. UK Finance. 2023. ANNUAL FRAUD REPORT 2022. https://www.ukfinance.org.uk/policy-and-guidance/reports-and-publications/annual-fraud-report-2023.
  11. Fraud detection in mobile payment systems using an XGBoost-based framework. Information Systems Frontiers 25, 5 (2023), 1985–2003.
  12. Pascal Hitzler and Md Kamruzzaman Sarker. 2022. Neuro-symbolic artificial intelligence: The state of the art. (2022).
  13. Differentiable Rule Induction with Learned Relational Features. arXiv preprint arXiv:2201.06515 (2022).
  14. PaySim: A financial mobile money simulator for fraud detection. In 28th European Modeling and Simulation Symposium, EMSS, Larnaca. Dime University of Genoa, 249–255.
  15. Brian W Matthews. 1975. Comparison of the predicted and observed secondary structure of T4 phage lysozyme. Biochimica et Biophysica Acta (BBA)-Protein Structure 405, 2 (1975), 442–451.
  16. Stephen Muggleton. 1991. Inductive logic programming. New generation computing 8 (1991), 295–318.
  17. Ali Payani and Faramarz Fekri. 2019. Inductive logic programming via differentiable deep neural logic networks. arXiv preprint arXiv:1906.03523 (2019).
  18. Deep symbolic regression: Recovering mathematical expressions from data via risk-seeking policy gradients. arXiv preprint arXiv:1912.04871 (2019).
  19. Learning accurate and interpretable decision rule sets from neural networks. In Proceedings of the AAAI Conference on Artificial Intelligence, Vol. 35. 4303–4311.
  20. Birgit Tausend. 1994. Representing biases for inductive logic programming. In European Conference on Machine Learning. Springer, 427–430.
  21. Explainable Fraud Detection with Deep Symbolic Classification. methods 2, 10 ([n. d.]), 17–28.

Summary

No one has generated a summary of this paper yet.

Paper to Video (Beta)

No one has generated a video about this paper yet.

Whiteboard

No one has generated a whiteboard explanation for this paper yet.

Continue Learning

We haven't generated follow-up questions for this paper yet.

Collections

Sign up for free to add this paper to one or more collections.

Tweets

Sign up for free to view the 1 tweet with 1 like about this paper.