SIGNATURE VERIFICATION SYSTEM USING MACHINE LEARNING

ABSTRACT The reliability and performance of real time fraud detection techniques has been a major concern for the financial institutions as traditional fraud detection models couldn’t cope with the emerging new and innovative attacks that deceive banks. The problems are further exacerbated with evolving customer behavior as existing fraud detection models unable to cope with class imbalance problem and longer feedback loop. The paper addresses the drawbacks of conventional rule-based systems, explains why real-time monitoring and machine learning should be used. This project looks at the holistic view of fraud detection and proposes a conceptual fraud detection framework that can detect anomalous transaction quickly and accurately, as well as dynamically evolve to maintain the efficiency with minimum input from subject matter expert. The suggested approach includes dimensionality reduction, data preparation, and the application of machine learning models built into a real-time monitoring system. As our major goal is to focus on fraud transaction prevention, we use linear regression algorithm to determine whether or not the transaction is valid. This is accomplished by using the provided dataset to learn. To achieve our objective, we built an application where you can register your details for login and submit card information for registration. The algorithms will then examine and identify the transactions. Results are assessed using performance measures and contrasted with the performance of current systems. The study suggests areas for additional research in this field and helps to design reliable fraud detection systems. Our developed system will be built using python programming language and data storage will be done using.