House Price Prediction Using Linier Regression

Property entrepreneurs will compete to build properties, especially houses for investment facilities. This will make house prices increase day by day with a high purchasing power of the people. Consumers will think in buying a house whether the house they buy will have a good profit value or not. The aim of the study is to build a model that may predict house price for company and become a business decision for consumers. The methodology used seven major steps namely, business understanding, data understanding, data cleaning, data standardization, modelling, and evaluation. This study develop a linear regression model for home price prediction and tests it using data from the Maribelajar company. These are carried out on the Azure Platform by creating two pipelines. One pipeline for training and another for testing. The results are then visualized using Power Business Intelligence for providing a proper business performance analysis. From the experimental results, the model achieved RMSE= 0.0334 and R coefficient = 0.7. The data analysis and testing in this study show that the multiple linear regression model can forecast and evaluate housing prices to some extent, but the algorithm may still be improved using more advanced machine learning approaches.