Latest Issue
The 15th Scientific day : Bridging Science, Engineering, Technology & Industry for Cambodia's Growth
Published: July 31,2026Comparison Analysis of Deep Learning and Tree-Based Homogeneous Ensemble Learning Predictive Models on the KHR/USD Daily Official Exchange Rate
Published: July 31,2026Comparing Time Series, Machine Learning, and Deep Learning Models for Paddy Rice Price Forecasting in Battambang Province, Cambodia
Published: July 31,2026The Forecasting for Cambodia’s Rice Production Using Multiple Linear Regression and Tree – Based Ensemble Learning Methods
Published: July 31,2026From Educational Model to Achievements - Classifying Post-Graduate Success with Machine Learning
Published: July 31,2026Analysis on Machine Learning Models for Imbalanced Data Problem in Payment Fraud Detection
Published: July 31,2026A Computational Approach to Labor Market Analytics: Analyzing Skill Trends in Cambodia Using an LLM-Based Pipeline
Published: July 31,2026Recognizing Khmer Handwritten Digits with the Power of Sequential RNNs
Published: July 31,2026KVerifyID: A Hybrid Multimodal Approach for Khmer Online Writer Verification
Published: July 31,2026Analysis on Machine Learning Models for Imbalanced Data Problem in Payment Fraud Detection
-
1. Department of Applied Mathematics and Statistic, Institute of Technology of Cambodia, Russian Federation Blvd., P.O. Box 86, Phnom Penh, Cambodia
Received: June 20,2025 / Revised: September 16,2025 / / Accepted: September 18,2025 / Available online: July 31,2026
Payment card fraud losses worldwide reached $33.83 billion in 2023 (Nilson Report, 2025). Alarmingly, Deputy Prime Minister and Minister of Interior Sar Sokha (2024) stated that in the first semester of 2024, Cambodians lost nearly $40 million to online and digital fraud. To prevent these significant financial losses, it's crucial to identify the predictive models that can more accurately detect the anomalies in transactions. This study investigates which predictive models work best in predicting the anomalies in the payment transaction. The dataset contains types of online transactions, the amount of the transactions, names of the sender and receiver, the sender’s balance of account balance before and after the transaction, and the receiver’s account balance before and after receiving money. Autoencoder, LightGBM, Neural Network, Logistic Regression, Random Forest, and CatBoost were built as prediction models within this research. Each of these algorithms is employed to create prediction models, which are meticulously fine-tuned to yield the most accurate prediction of the fraud payment in the system involving optimizing hyperparameters and selecting the best features to enhance the models’ prediction power. Common performance metrics such as Precision, Recall, F1-Score, and AUC-ROC were used to test each model's performance. Extensive experimentation data shows the best performance of CatBoost (AUC-ROC of 0.895 for Oversampled and 0.999 for other kinds of datasets) and Random Forest model (AUC-ROC of 0.99), which consistently outperforms other machine learning methods in accurately predicting payment fraud, whether training with an imbalanced or balanced dataset. These results highlight the model's ability to handle complex, non-linear relationships within the data and its effectiveness in generalizing across different scenarios and conditions. In conclusion, the findings of this study will be beneficial mostly to the banking system as they can apply the models we found in their system to prevent any fraudulent activities. Spotting the fraudulent activities in the early stage plays an immense role in preventing the loss.