Correlation Analysis of Voting Regression and Decision Tree Algorithm to Predict House Price with Improved Accuracy Rate

Abstract

The primary goal of this study is to use efficient machine learning algorithms to anticipate better house prices, typically inflated. Materials and Methods: : This study will study the differences between near-accurate price prediction utilizing Novel Voting Regression (Group 2) and Decision Tree methods (Group 1). The sample size used to carry out this research was N=10 for each group studied. Clincle was used to calculate the sample size. The pre-test analysis was maintained at 80%. G-power is used to calculate the sample size. Statistical analysis yielded a significance value of 0.001. Results: : The accuracy of the Novel Voting Regression Algorithm for house price prediction is 82.94%, which is greater than the Decision Tree Algorithm's 72.54%. The Independent Sample T-test has a statistical significance of 0.584. Conclusion: : As a result, it can be stated that the Novel Voting Regression technique can produce results that are almost as accurate as of the Decision Tree technique.