The Real Estate Price Prediction Based on Multivariate Linear Regression Models

Abstract

The price of households had increased greatly as the demands in the market increased. Real estate had become the most popular method to resist inflation. Thus, more experts and scholars are working on the research in this area, including but not limited to find the future trends of housing prices and the possible bubble of housing prices. This paper will use the basic data regression model in Excel, powered by Microsoft, to find the factors that lead to the appreciation or depreciation of real estate, and three different methods of dealing with the data will be applied which are standardization, interception, and normal normalization. As a result of complex processes, normalization is the best way to deal with the data that was chosen from Kaggle. In the meantime, a linear correlation was done for checking the independency of each variable, and turned out to be successful. According to the analysis, an inverse relationship between the variables house age and distance nearest to the store was found, and the lower the house age is, the higher the price is, higher the house age is, lower the price is. The main aim of this paper is to investigate the relationship of the factors and their impact of them on the price of the house, was achieved and solved mathematically, and therefore, this research paper has found its goals. These results shed light on guiding further exploration of house price estimation.