Integrating Autoencoders with Local Outlier Factor and Isolation Forest for Effective Fraud Detection in Imbalanced Datasets

Abstract: It is highly challenging to detect fraudulent transactions with extant imbalances in available datasets where fraudulent cases make up a minor percentage of total transactions. This work presents a novel hybrid anomaly detection framework that integrates Autoencoders for efficient dimensionality reduction with LOF and Isolation Forest algorithms to detect anomalies for accurate fraud detection. We make use of the very standard dataset, namely Credit Card Fraud Detection Dataset [7], that has 284,807 transactions of which only 492 are classified as fraudulent. We apply Synthetic Minority Over-Sampling Technique to balance the dataset for optimizing the model’s performance. The results show that although LOF is challenging in terms of precision, it exhibits significant increases in recall with the proper adjustment of the contamination parameter and utilization of SMOTE. In comparison, Isolation Forest algorithm works excellently in terms of recall where it detects 81% frauds but degrades slightly in terms of precision after using SMOTE. The two techniques here have trade-offs between precision and recall, hence indicating a scope for further optimization. Both LOF and Isolation Forest significantly contribute in detecting anomalies in imbalanced datasets, and though Isolation Forest has a higher efficiency ratio compared to LOF in fraud transaction detection, our results confirm that indeed using Autoencoders for the extraction of features and advanced anomaly detection techniques have a synergistic effect in fraud detection applications, particularly in big class imbalance scenarios. Future research would include other oversampling techniques along with fine-tuning the parameter settings to have a better balance between precision and recall.