Enhancing Financial Fraud Detection through Machine Learning: A Comparative Study of Anomaly Detection and Classification Models on Imbalanced Datasets

DOI

10.2991/978-94-6463-906-3_18How to use a DOI?

Keywords

Isolation Forest; Decision Trees; Logistic Regression; Random Forest; XGBoost; Financial Fraud Detection

Abstract

Financial fraud poses an escalating global threat, fueled by the proliferation of electronic payment systems. As traditional methods of monitoring and detection struggle to keep up with the vast number of daily transactions, the need for automated fraud detection systems has become paramount. This paper explores the application of machine learning techniques to detect fraudulent financial transactions in imbalanced datasets. I evaluate two datasets: one synthetic and one anonymized real-world dataset of European credit card transactions. A variety of machine learning models, including Isolation Forest, Decision Trees, Logistic Regression, Random Forest, and XGBoost, were trained to classify fraudulent transactions. Techniques such as ADASYN were used to balance the datasets and improve model performance. Initial results demonstrate that traditional classifiers like XGBoost and Random Forest offer superior performance in both datasets, achieving high accuracy, precision, and recall. Feature engineering and dimensionality reduction were further employed to optimize computational efficiency without significant loss in performance. This study highlights the effectiveness of ensemble learning and anomaly detection in financial fraud detection and underscores the importance of data preprocessing and feature selection in improving model accuracy on imbalanced datasets.

Copyright

© 2025 The Author(s)

Open Access

Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

TY  - CONF
AU  - Ravinder Singh
PY  - 2025
DA  - 2025/12/12
TI  - Enhancing Financial Fraud Detection through Machine Learning: A Comparative Study of Anomaly Detection and Classification Models on Imbalanced Datasets
BT  - Proceedings of Botho University International Research Conference (BUIRC 2025)
PB  - Atlantis Press
SP  - 313
EP  - 324
SN  - 3005-155X
UR  - https://doi.org/10.2991/978-94-6463-906-3_18
DO  - 10.2991/978-94-6463-906-3_18
ID  - Singh2025
ER  -