Relative Analysis of Random Forest Classification over Support Vector Machine Classifier for Credit Card Cyber Thefts Detection with Reduced False Rate
E Madhan Mohan, S. John Justin Thangaraj · 2023
This research study aims to find a way to reduce the number of times that a false identification mistake occurs during a cybercrime involving a credit card transaction by making use of a binary selection of a new Random Forest classifier and Support Vector Machine. The goal of this study is to find a way to reduce the number of times that a false identification mistake occurs. The detection of any malware attacks is the primary purpose of this project; the information gathered in this regard need to be sent simultaneously to the user of the credit card as well as the investigator. Grouping was figured out for the sake of this study by using a Random forest classifier (N = 28) rather than a Support Vector Machine (N = 28) to figure out the error rate. In the statistical test, there is not a significant difference between g-power 0.08 and alpha values. This difference is either less than 0.05 or equal to 0.05. The data set is analyzed by using the Independent sample T test, and the confidence interval is set at 95%. This fake news detection difference has a statistical significance of 0.03 (p 0.05), which shows that the findings of the studies included in this study are significant. A comparison of the Random forest classifier and the support vector machine was carried out in order to meet the requirements of this investigation so that it could be carried out. The accuracy of the support vector machine is 91.four percent, whereas the accuracy of the random forest classifier is 94.4 percent, making the random forest classifier more accurate.