An integrated Machine Learning framework for fraud detection: a comparative and comprehensive approach

Ouazzane, Karim, Polykarpou, Thekla, Patel, Yogesh and Li, Jun (2022) An integrated Machine Learning framework for fraud detection: a comparative and comprehensive approach. International Journal of Information Security and Privacy (IJISP), 16 (1). pp. 1-17. ISSN 1930-1650


The research develops a practical Machine Learning framework with a comparative and comprehensive approach to sequence-learn and then detect the online banking payment fraud. The integrated framework introduces exploratory analysis and feature engineering, multiple modelling and performance comparison, and model robustness, uncertainty and sensitivity analysis toward a systematic approach for Machine Learning applications. For demonstration purpose, the framework is implemented on a set of real-life online banking transaction datasets obtained from a UK-based bank through three models, i.e., Support Vector Machine, Markov Model and LSTM model, with various combinational features of the datasets evidenced in the exploratory analysis and modelling with noise ratios of datasets, range values of model parameters and confidence intervals of prediction results. The modelling results show that overall, the LSTM model achieves the best performance, with outcome accuracy of 97.7%, indicating its advantage in modelling sequential data such as customer behaviours over other models. The SVM-4 model among all the SVM models and the Markov model with sampling rate of 5s among the Markov models give the best results in their own category. The research highlights an adoption of multiple machine learning approach with model uncertainty and sensitivity analysis to compare the results, raise the statistical confidence and enhance the model accuracy and robustness. The future research will explore the distributed training by deploying the framework in a High-Performance Computing environment. The theorization of the comparative and comprehensive approach for general-purpose fraud detection will also be accomplished.

An integrated Machine Learning framework for fraud detection.pdf - Accepted Version
Restricted to Repository staff only

Download (855kB)
View Item View Item