Volume-11, Issue-5, May 2025

Abstract

The surge in digital financial activity has led to increasingly sophisticated forms of fraud, creating serious challenges for financial institutions. One of the core obstacles in fraud detection is the substantial class imbalance present in transactional datasets, where fraudulent records represent a small minority. This study presents a robust machine learning framework that integrates the Synthetic Minority Over-sampling Technique (SMOTE) with three distinct classifiers—XGBoost, Long Short-Term Memory (LSTM), and K-Nearest Neighbors (KNN)—to enhance the detection of fraudulent activities. Using a real-world dataset of six million banking transactions, we assess each model’s performance through accuracy, precision, recall, F1-score, and both PR and ROC AUC metrics. Our findings show that SMOTE significantly boosts model recall and AUC scores. Among the models, XGBoost consistently delivers superior results with near-perfect metrics, while KNN maximizes recall, albeit at a slight cost to precision. LSTM produces more moderate but stable performance. Visual diagnostics, such as ROC/PR curves and confusion matrices, further confirm the reliability of XGBoost when combined with SMOTE. Overall, the integration of data balancing with advanced classifiers proves to be a powerful approach for real- time fraud detection.

Keywords: Financial fraud detection, imbalanced datasets, machine learning, XGBoost, SMOTE.

References

Keywords: Financial fraud detection, imbalanced datasets, machine learning, XGBoost, SMOTE.

Abstract

India, like many nations, faces the dual challenge of increasing transportation demands and growing environmental concerns. In this context, electric vehicles (EVs) have emerged as a potential game-changer, promising a cleaner and more sustainable alternative to traditional fossil fuel-powered vehicles. This study explores perceptions and experiences of 30 electric vehicle (EV) users, focusing on socio-demographics, usage patterns, challenges and satisfaction. The sample was predominantly male (83.3%), with a balanced age distribution and a high proportion of private-sector employees. Most respondents owned electric two-wheelers, auto-rickshaws and cars, with over 40% using EVs for more than three years. Cost savings on fuel emerged as the primary motivation for EV adoption. While most users reported home charging as convenient, issues such as high initial costs, limited fast-charging infrastructure and range anxiety were noted. Respondents generally recognized EVs' environmental benefits and lower running costs. A majority expressed satisfaction with their EV experience and recommended them to others. The findings highlight the importance of enhancing affordability, technological reliability and policy support to accelerate EV adoption in India.

Keywords: Electric Vehicles, Technology, Environment, Cost Effective, Government Policies.

References

Keywords: Electric Vehicles, Technology, Environment, Cost Effective, Government Policies.