2026-10-15T10:58:13Z https://api.figshare.com/v2/oai

oai:figshare.com:article/25310197 2026-05-29T01:40:41Z category_29161 portal_923 item_type_3 month_year_05_2026

Fraudulent Transaction Detection and Prevention Using Deep Neural Networks Mohammed Uddin (11498878) Deep learning Artificial intelligence Fraudulent transaction Deep Learning Deep Feature Synthesis Hyperparameter tuning Convolutional Neural Network Grid Search Random Search The research is for the detection and prevention of fraudulent financial transactions that happened in different business organizations by using deep learning technique, a neural networks model of Artificial Intelligence system. The objective of the project is to find out the best fraud detection model by comparing it with existing machine learning and deep learning techniques used for fraud detection. This study focuses on detecting fraudulent transactions using deep learning techniques, specifically Convolutional Neural Network (CNN) models. A systematic literature review is conducted to address research questions, exploring six experimental steps for fraudulent transaction detection using deep learning. The integration of DFS improves fraud detection performance, resulting in a notable enhancement in recall, F1 score, and accuracy. Hyperparameter tuning, utilising grid search and random search algorithms yield remarkable improvements across precision, recall, and F1 score for the optimised CNN models compared to the baseline. These optimised CNN models surpass the baseline and outperform a state-of-the-art method.<p></p> 2026-05-29T01:40:41Z Dataset Dataset 10.25946/25310197.v1 https://figshare.com/articles/dataset/Fraudulent_Transaction_Detection_and_Prevention_Using_Deep_Neural_Networks/25310197 All Rights Reserved 1.0