The Effect of Best First Search Optimization on Credit Card Fraudulent Transaction Detection

Abstract

In the digital world, Recently growth of online shopping site for purchasing clothes, electronic items, glossary etc and online transaction for transfer money is increasing day by day . At the same time, criminals have become able to doing fault and earning money through wrong ways .that’s why fraud grows. With the development of Machine Learning in the field of Computer Science and Engineering, its application in the different domain also in fields like Medical, Marketing, Telecommunication, finance, etc. The reason for the popularity of Machine Learning in these domains is due to its high accuracy prediction. That’s why over many years, machine learning has been used in fraud detection. With the advancement of technology in online transactions, fraud is the greatest issue for businesses and has become difficult to recognize than the traditional form of this crime. Historically, the area of Fraud Detection is interrelated to Data Mining & Text Mining. Due to the sudden growth of fraud whose outcome is loss of trillions of rupees worldwide every year, various modern techniques in detecting fraud were proposed that are progressed without interruption and applied to many business fields. Bank frauds worth ₹2.05 trillion happened in the last 11 years, among which there were overall 53,334 fraud issues in the usage of RBI data. The principle purpose behind this write up is to review different methods in identifying frauds corresponding to the unusualness in the transactions. The supervised and unsupervised machine learning algorithms will be used to identify fraud and the best first search optimization will be analyzed to compare both results, i.e., before and after optimization

Financial revolution: a systemic analysis of artificial intelligence and machine learning in the banking sector

“…In tests on real data from a bank, the DT achieved a prediction accuracy of 94.39%, outperforming other models. On the other hand, Sahu et al [19] apply AI and ML models to bank fraud detection, particularly aimed at identifying deceitful credit card transactions. Based on the experimental findings of the different supervised models, naive bayes and SVM are 97% accurate, and logistic regression is 99% accurate in detecting credit card fraud.…”