Perbandingan Akurasi Algoritma Regresi Linier

Abstract

Along with technological advances, there is an approach to giving consideration when buying a house by analyzing prediction system. Research related to the accuracy comparison of the algorithm on the house price prediction gets conducted for precise prediction results. The algorithms used are Linear Regression, Polynomial Regression, and Support Vector Regression. The goal is as a reference for developers to be able to use the suitable algorithm and can provide accurate house price predictions. Linear Regression algorithm modeling produces a prediction score of 69% with a coefficient of determination (R2) of 0.69 and an RMSE value of 4395785322.216207. Support Vector Regression algorithm makes a prediction score of 97% with a coefficient of determination (R2) of 0.97 and an RMSE value of 31.19812999869066. Polynomial Regression algorithm modeling has a prediction score of 99% with a coefficient of determination (R2) of 0.99 and an RMSE value of 0.000403824405323. Based on these results, it can consider that the modeling of the house price prediction system with Polynomial Regression has the best level of accuracy.