Improving the accuracy of predicting the cybercrime using novel random forest algorithm over support vector machine

Abstract

The purpose of this study was to assess the accuracy of cybercrime predictions provided using Novel Random Forest and Support Vector Machine. Material and Procedure: Cybercrime predictions were made using the new random forest (N=10) and the support vector machine (N=10), which were then analysed. Random forest trumps SVM in terms of precision (by a margin of 84 percent to 85 percent ). 81 percent is the percentage. The advanced random forest classifier performed better than the conventional SVM classifier. There is a significant difference in accuracy between the two approaches (p>0.005). The development of the new cybercrime prediction system used machine learning. This novel random forest technique outperformed SVM.

Related Papers

• → An Optimized Random Forest Classifier for Diabetes Mellitus(2018)36 cited
• → Face classification by a random forest(2007)24 cited
• → Margin based variable importance for random forest(2011)4 cited
• → Feature Selection In Support Vector Machine And Random Forest Algorithms For The Classification Of Recipients Of The Smart Indonesia Program(2024)1 cited