AN INTELLIGENT ML-BASED SYSTEM FOR IDENTIFYING ANOMALIES IN UPI PAYMENT NETWORKS

Read full text Summarise with VIRAT
Authors: Kavi Karthick T, Ajay Kumar M, Dr.G.A.Senthil, K. Arthi
Cited by: 0

Summary

No summary yet. VIRAT can read this paper and write a plain-language summary of its aim, methods, key findings and limitations.

Summarise with VIRAT Free to try with your Science Catalogs account.

Abstract

As adoption of UPI for online transactions is on the rise, fraud has also been rising sharply. This project applies machine learning to identify UPI fraud in real time with the help of Random Forest algorithm. The model was trained using a dataset that includes transaction information such as amount, time, sender and receiver activity, device data. Data preprocessing steps such as dealing with missing values, feature scaling, encoding the categorical variables, feature selection were utilized to enhance the performance of the model. Random Forest algorithm which is strong and can deal with big data creates an ensemble of many decision trees and aggregates their prediction to achieve higher accuracy of 96% and lower overfitting. The model achieved a precision of 97%, recall of 91%, and an F1-score of 93%, indicating its strong capability to accurately detect fraudulent transactions while minimizing false positives and false negatives. Results of experiments reveal that the model is capable of identifying fraudulent transactions with high accuracy and recall. The system includes user friendly interface that gives real time fraud detection, transactional monitoring and fraud alerts. With the use of machine learning in digital payment security this project offers a trustworthy means to prevent UPI fraud and enjoy secure financial transactions.

Fields of Study & Subjects

Imbalanced Data Classification Techniques Privacy-Preserving Technologies in Data Network Security and Intrusion Detection

Publication details

Journal / source
Zenodo (CERN European Organization for Nuclear Research)
Publication date
23 March 2026
Language
EN
Document type
Book