Higher Accuracy of Malicious Websites Prediction using Logistic Regression Algorithm Comparing with Decision Tree Algorithm

Authors

  • Ch. Sai Venkatesh
  • L. Rama Parvathy

Keywords:

Innovative Malicious Website Prediction, Machine Learning, Logistic Regression Algorithm, Decision Tree Algorithm, Statistical Analysis, Supervised Learning.

Abstract

Aim: The fundamental goal of the research study is to work on the accuracy of a prediction of malignant sites utilizing the Logistic Regression (LRA) machine learning algorithm against the Decision Tree Algorithm (DTA) .Materials and Methods: The review utilized 20 samples with two groups of algorithms with the G-power worth of 85% percent and the malicious attack information were gathered from different web sources with late findings and threshold 0.05% and confidence interval 97% with mean and standard deviation. To anticipate the vindictive assaults by further developing the Logistic Regression Algorithm has been viewed as 97% of precision, consequently this concentrate needs to find the better exactness for noxious Attack expectation with the Decision Tree Algorithm Algorithm machine learning algorithm. Result: This examination concentrated on saw as 85% of precision for sites utilizing the Decision Tree calculation with a critical worth of  two tailed tests is 0.001(p<0.05) with 97% confidence interval. Conclusion: This study presumes that the Logistic Regression calculation on Innovative malevolent site Prediction is essentially better compared to the Decision Tree Algorithm.

Downloads

Published

2022-12-13