Suspicious Activity Detection Model in Bank Transactions using Deep Learning with Fog Computing Infrastructure
Girish Wali, Chetan M. Bulla · Advances in computer science research · 2024
The banking sectors are facing several challenges in detecting and preventing different types of cyber attacks.The main challenge is to find the suspicious activities in money transactions.The majority of Financial institutions are commercial banks suffers lot due to these cyber attacks.The time critical applications requires very small latency in providing services and Cloud computing infrastructures are not well-suited for time-sensitive applications as it takes more latency.Thus, fog computing, an innovative computing paradigm, is utilized to reduce communication latency.The tradition, statistical and machine learning methods effectively identified suspicious activity, but accuracy and trade off between recall and precision is very less.IN this paper a novel suspicious activity detection model is proposed using deep learning with natureinspired algorithm, to improve the accuracy.The proposed approach analyses transactional patterns in historical data and classify the suspicious and nonsuspicious actions.The simulation model is developed using Python programming language and the Google Colab framework to evaluate proposed model.The simulation results show improved accuracy compared to existing state of art works