CCNN: An Artificial Intelligent based Classifier to Credit Card Fraud Detection System with Optimized Cognitive Learning Model

Nowadays digital transactions play a vital role in money transaction processes. Last 5 years statistical report portrays the growth of internet especially credit card and unified payments interface. Mean time increasing numerous banking threats fraud rates also growing significantly. Data engineering techniques provide ultra supports to detect forgery problems online offline mode transactions. This detection (CCFD) prevention-based data processing issues raising because two major reasons first, classification rate legitimate uses is frequently changing, next one dataset values are vastly asymmetric. Through this research work investigating performance various existing classifier with our proposed cognitive convolutional neural network (CCNN) classifier. Existing classifiers like Logistic Regression (LR), K-nearest neighbor (KNN), Decision Tree (DT) Support Vector Machine (SVM). These models facing challenges low high complexity hit accuracy. we introduce learning-based CCNN methodology artificial intelligence for achieve maximum accuracy minimal issues. For experimental analysis attained from specific region cardholders containing 284500 its features. Also, contains unstructured non-dimensional converted into structured help over sample under method. Performance shows model significant improvement on accuracy, specificity, sensitivity rate. The results shown comparison. After cross-validation, algorithm fraudulent archived 99% which using over-sampling model.