Advanced CNN-LSTM Framework for Mobile Transaction Security in E-Commerce Fraud Detection

The rise of technology has led to an increase in fraudulent activities in e-commerce, particularly in mobile commerce, posing significant risks to transaction security. Traditional fraud detection methods struggle to address this challenge as fraudsters employ sophisticated techniques that mimic legitimate user behavior, resulting in high false positive rates and missed fraud attempts. To overcome these limitations, this study proposes a novel fraud detection solution combining Convolutional Neural Networks (CNNs) and Long Short-Term Memory (LSTM) networks. CNNs are utilized to extract geographical features from transaction data, while LSTMs analyze temporal dependencies. This dual approach enhances flexibility and effectiveness in detecting fraudulent activities, regardless of transaction volume or complexity. The proposed methodology demonstrates a significant improvement over existing methods, achieving an accuracy of 99.6%. This advanced system strengthens mobile commerce security, offering robust protection against emerging fraud threats, benefiting both consumers and e-commerce businesses.