House Price Prediction Based on Joint Clustering and Linear Regression

Abstract

The corona virus disease (COVID-19) epidemic has a great impact on the real estate industry. The epidemic has caused a downward trend in housing values. It is essential for those who want to buy property during this period of economic recovery to understand the key factors influencing house pricing. In order to identify the factors that influence real estate prices and make house price prediction, this study uses a mathematical model called linear regression to analyze the data. The model is further improved and streamlined by focusing on essential elements. The study successfully pinpoints the most critical factors affecting home prices and makes relatively accurate house price prediction. Notably, the house's number of levels and bedrooms are essential determinants for house price prediction. Understanding these variables enables real estate agencies to concentrate on particular areas for improvement, thereby optimizing the total housing market, which gives buyers a clearer idea of the types of homes they can pick. Real estate brokers can work more productively, increase their competitive edge, and guarantee long-term success in the post-pandemic recovery phase. Furthermore, by building homes with more logical conditions for buyers, brokers may protect their brand identity and nurture client loyalty.