Housing Price Prediction Using Machine Learning

Abstract

As housing price increases annually, offering unusual prices for houses that are not worth so much is a current problem faced by those who plan to buy a house. Moreover, most property investors also mislead by using fake facts without knowing the trend of houses for a certain location. So, the proposed system allows to evaluate the performance and the predictiveness of a model that supervises collected data from a certain area. The system is stricter on providing accurate values for the houses than the existing systems. This project expects to build a good mutual understanding between buyer and seller. It will endeavor to give the best rates among different calculations when utilizing the public dataset in preparing realworld. The project shows the factors that are affecting Housing Price Prediction on real-world. Furthermore, the observational outcomes show that crime rates, store rates, and public spots impact the house costs contrarily, whereas expansion, year, and joblessness rate sway the house costs emphatically. Overall, in the modern world, with the rapid development of technology and digitalization, a software like this is really required to defend from sellers, who deceive customers verbally and physically by showing inaccurate prices for properties which are not worth that much. It will help investors to achieve their economic ideas without any doubt too