Downloads: 3 | Views: 232 | Weekly Hits: ⮙1 | Monthly Hits: ⮙2
Research Paper | Decision Science | United States of America | Volume 13 Issue 10, October 2024 | Rating: 5.4 / 10
An Overview of Classification Techniques and Methodologies for Fraud Detection
Vinay Kumar Yaragani
Abstract: Fraud detection is a critical challenge in today's data-driven world, requiring precise and effective techniques to identify and mitigate fraudulent activities across industries. This paper provides a comprehensive overview of advanced classification techniques employed in fraud detection, highlighting their strengths and limitations. We delve into traditional methods, such as logistic regression and decision trees, as well as more sophisticated approaches like ensemble techniques and deep learning models. The paper also outlines a systematic methodology for building a robust fraud detection framework, from data preprocessing and feature engineering to model evaluation and deployment. Emphasizing practical strategies and real-world applications, this study aims to equip organizations with the knowledge to proactively detect and combat fraud, ultimately safeguarding their operations and enhancing trust in their systems.
Keywords: Fraud Detection, Buyer Satisfaction, Risk Management, Anomaly Detection, Predictive Analytics
Edition: Volume 13 Issue 10, October 2024,
Pages: 927 - 933