Jul 2026· International Scientific Journal of Engineering and Management· Vol 05, pp. 1-9· 0 citations
TL;DR
This project presents an ML-Based Real-Time UPI Fraud Detection System that uses machine learning algorithms to identify fraudulent transactions efficiently and shows that the Random Forest algorithm achieves the highest accuracy, making it the most effective model for fraud detection.
Abstract
ABSTRACT The rapid growth of Unified Payments Interface (UPI) transactions has increased the risk of online payment fraud. This project presents an ML-Based Real-Time UPI Fraud Detection System that uses machine learning algorithms to identify fraudulent transactions efficiently. The system preprocesses transaction data by handling missing values, encoding categorical features, and splitting the dataset for training and testing. Machine learning models such as Support Vector Machine (SVM), Random Forest, and AdaBoost are trained to classify transactions as genuine or fraudulent. The models are evaluated using accuracy, confusion matrix, and classification metrics. Experimental results show that the Random Forest algorithm achieves the highest accuracy, making it the most effective model for fraud detection. The proposed system enhances the security of digital payment platforms by enabling real-time fraud detection, reducing financial losses, and improving the reliability of UPI transactions.
Keywords: UPI, Fraud Detection, Machine Learning, Random Forest, Real-Time Detection, Digital Payments.
A UPI Fraud Detection System using the Random Forest machine learning algorithm that helps banks and digital payment platforms identify suspicious transactions quickly, reducing financial losses and improving user security.
Avu Siva Dinesh Kumar, G. Kumar· International Journal for Re...· 0 citations
An AI-Based Credit Card Fraud Detection System using Machine Learning to identify suspicious transactions accurately and in the real time and improves prediction accuracy through sequential learning and optimized decision trees.
P. Ravikumar, Gowrav A. S., A. N et al.· International Journal of Inn...· 0 citations
The rapid growth of digital banking has increased the number of online transactions, making fraud detection an important challenge for financial institutions. This project presents a real-time bank transaction fraud detection system that combines Apache Kafka with Machine Learning to identify suspicious transactions as they occur. Apache Kafka is used to stream transaction data continuously, while a Random Forest classifier analyzes each transaction and predicts whether it is genuine or fraudulent. Before training the model, the transaction dataset is cleaned, encoded, and normalized to improve prediction accuracy. A Flask-based web application provides an easy-touse interface for generating transaction streams and displaying fraud detection results in real time. The proposed system reduces the delay associated with traditional batch-processing methods and enables faster decision-making. Its modular design also allows the system to handle increasing transaction volumes, making it suitable for modern banking environments that require secure, reliable, and scalable fraud detection solutions.
Thakur Nivedita Singh, P. Paul· International Journal of Dat...· 0 citations
: Frictionless peer-to-peer and merchant payments made possible by India's Unified Payments Interface (UPI) systems' rapid expansion. Nevertheless, the increase in transaction volume has also led to a rise in fraudulent activity, including as bot-driven transactions, phishing, and QR code manipulation. Rule-based algorithms and static machine learning classifiers, two traditional methods of detecting fraud, find it difficult to keep up with changing fraud strategies. In order to identify fraudulent UPI transactions, this study suggests a machine learning system that combines ensemble learning methods, deep learning architectures, and sophisticated feature engineering. For accuracy and interpretability, the system combines hybrid ensembles (CNN + Random Forest), transformer-based models for sequential transaction analysis, and graph neural networks (GNNs) for relational modeling. Preprocessing methods including feature scaling, categorical encoding, and data balancing algorithms like SMOTE are applied to a sizable, real-world UPI dataset. Through experiments, the suggested framework outperforms baseline models, obtaining a ROC-AUC of 0.996, 99.4% accuracy, and 98.7% precision. Furthermore, disclosure is enhanced by explainable AI (XAI) methods like SHAP, and sfraud detection across banks is protected by federated learning. This study increases UPI security against changing fraud tactics by providing a scalable, real-time, and interpretable architecture.
N. Siva, K. Durgadevi, J. Jyothi et al.· Proceedings of the 1st Inter...· 0 citations
The study shows that machine learning can be useful for fraud detection when it is combined with suitable preprocessing, class-imbalance techniques, and careful evaluation.
Jabulani Khumalo, Min Joon Kim· Global Knowledge Academy· 0 citations
Financial transaction fraud is an ongoing threat with significant economic loss and on customers' trust. This paper discusses Fraud Detection in detail with machine learning technique on a given data set of a transaction. We investigate the patterns revealed from the users and the transactions in the database when the user is performing fraudulent transactions, and test several classification models that can be used to detect fraud, which includes logistic regression model, random forests, support vector machines, gradient boosting, and neural networks. The performance of the models is investigated in terms of accuracy, precision, recall, F1 score and ROC-AUC metrics. Based on our experiments, the best detection overall performances are obtained for the tree-based ensemble models (Random Forest and XGBoost) with XGBoost getting the most optimum fraud Recall and F1-Score. Through the data analysis results (such as account age, transaction frequency etc.) and the model comparison, we expound an improved method which is based on combining the ensemble of best models with data imbalance countermeasures to increase the recall of fraudulent cases. We also have an end-to-end machine learning pipeline on Python to detect frauds from preprocessing the data, training the models, evaluating them, and deploying for fraud prediction. Also, a literature review of twenty-five recent studies on fraud detection is given, and the algorithms used, datasets and major contributions of these studies were summarized. The textbook ensemble technique, as proposed gives better fraud detection performance as it gains on the order of ~3-5% improvement against the best single model performance on F1-score, with acceptable precision, thereby underscoring the usefulness of hybrid modeling with specialized techniques for this field. The results emphasize that utilizing various models and domain-specific feature engineering can be of great benefit in fraudulent transaction detection, while also neg
