Analisis Perbandingan Metode Regresi Linier, Random Forest Regression dan Gradient Boosted Trees Regression Method untuk Prediksi Harga Rumah

The need for a place to live is one that many people prepare, both millennials and adults the elderly. With continued increase in population growth Indonesia increasing public interest buying early on, this can make not all groups of have or house quite livable. Related this, needs up-to-date information related predictions prices housing second-hand planning purposes future. purpose study carry out comparative analysis prediction results with several Machine Learning algorithms consist Linear Regression, Random Forest Regression Gradient Boosted Trees Regression. Evaluation method applying Cross-Validation. evaluation seen from smallest Root Mean Square Error (RMSE) error rate each testing method. are obtained an RMSE value 0.440, model 0.515 0.508. were dataset 2011 records division 80% data training 20% testing, has 6 attributes used including prices, land area, building number bathrooms, bedrooms garages. In study, using yielded highest accuracy 81.5% compared methods.