• Kumar Ujjawal
• Prof. Suresh. S. Gawande

Cloud computing and mobile computing have increasing its performance with rapid manner through numerous area of applications, these are extending such as digital payments, storage and confidential information accessing. Current technology offers several internet applications by using cloud based electronic payment methods, therefore security and confidentiality is necessary. According to national herald in India 42% frauds are identified in various fields from 1990 to 2020. Like “no fraud” agency in USA identified around 30% frauds since 1990, every year these frauds are increases with high ratios. Frauds did not have particular patterns, also change their behavior at every time. These frauds are most probably recognized at cloud based e-commerce and trade business websites. In order to decrease this frauds ratio, we need to develop a real and accurate fraud detection system. In this research with the help of deep and machine learning optimization methods has been used to detect the cloud based frauds. So many, existed works solve this issue but accuracy, F- score, recall and precession are very less. Because of this limitation, in this work is introduced deep learning mechanisms like fully Edited Nearest Neighbor (ENN) and deep neural network (DNN). The DNN with ENN is best technique for credit card fraud prediction and achieve good accuracy.

Credit Card, Deep Learning, ENN, DNN, Accuracy

"Optimization Accuracy of Credit Card Fraud Prediction using Deep Learning Neural Network", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.10, Issue 1, page no.d418-d423, January-2023, Available :http://www.jetir.org/papers/JETIR2301351.pdf

"Optimization Accuracy of Credit Card Fraud Prediction using Deep Learning Neural Network", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.10, Issue 1, page no. ppd418-d423, January-2023, Available at : http://www.jetir.org/papers/JETIR2301351.pdf