Scholarlink

Credit card fraud has become a critical issue with the rise of digital transactions, necessitating advanced detection mechanisms. This project presents a Django-based fraud detection system leveraging machine learning and deep learning models, including Support Vector Machines, Naive Bayes, Logistic Regression, Decision Trees, and XGBoost, optimized for high accuracy. The system processes transaction data in real time, utilizing SMOTE for class imbalance handling and structured databases for efficient data management. With an interactive web interface, it provides fraud detection visualizations through pie charts, bar charts, and splines while allowing service providers to download prediction datasets and monitor performance. XGBoost emerged as the most effective model, achieving 99.9% accuracy, demonstrating the system’s scalability and reliability in real-world fraud prevention.

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Machine Learning Approach for Fraud Detection in Banking Data

  • 会议论文

  • 发表日期：

    2026年

查看全文
  • M. Sai Lakshmi Sarvani,
  • D. Rajani,
  • K. Rohan Reddy

摘要

Credit card fraud has become a critical issue with the rise of digital transactions, necessitating advanced detection mechanisms. This project presents a Django-based fraud detection system leveraging machine learning and deep learning models, including Support Vector Machines, Naive Bayes, Logistic Regression, Decision Trees, and XGBoost, optimized for high accuracy. The system processes transaction data in real time, utilizing SMOTE for class imbalance handling and structured databases for efficient data management. With an interactive web interface, it provides fraud detection visualizations through pie charts, bar charts, and splines while allowing service providers to download prediction datasets and monitor performance. XGBoost emerged as the most effective model, achieving 99.9% accuracy, demonstrating the system’s scalability and reliability in real-world fraud prevention.