Copyright © 2026 Authors retain the copyright of this article. This article is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

@article{207097,
        author = {Diksha Gade and Ismita Nandini and Ritika and Rahul Mishra},
        title = {AI-Based Analysis and Detection of Spam Calls and UPI Fraud},
        journal = {International Journal of Innovative Research in Technology},
        year = {2026},
        volume = {13},
        number = {no},
        pages = {20-24},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=207097},
        abstract = {Modern financial transactions and user interactions have been revolutionized by the development of digital communication technologies and online payment systems, especially the Unified Payments Interface (UPI). But this expansion has also led to an increase in fraudulent activity and spam calls, which puts user privacy, financial stability, and confidence in digital platforms at grave risk. Because these threats are constantly changing, traditional rule-based detection techniques frequently fall short, underscoring the need for more sophisticated and automated solutions. An artificial intelligence (AI)-based system for the identification and evaluation of fraudulent UPI transactions and spam calls is presented in this study. The system analyses big datasets and finds trends in user behaviour and transaction history using machine learning (ML) methods. Important parameters include call frequency, call duration, repetition patterns, user interaction behaviour, and anomalies in transactions such as unusual amounts, irregular timing, and unknown recipients. The inclusion of user feedback and historical data further improves the accuracy and reliability of the system.
The suggested methodology uses predictive and anomaly detection methods to provide real-time monitoring and early fraud detection. It continuously gains knowledge from fresh data, which enables it to adjust to evolving fraud trends and gradually enhance performance. Developing a safe and effective system that lowers financial risks and increases user confidence in digital payment and communication platforms is the goal of this research. A rule-based risk score technique based on transaction amount and keyword analysis is used to detect UPI fraud, while TF-IDF is used for feature extraction and Logistic Regression for spam categorization.},
        keywords = {Artificial Intelligence (AI), Anomaly Detection, Cyber Security, Digital Payments, Machine Learning (ML), Spam Call Detection, UPI Fraud Detection.},
        month = {July},
        }