House Price Prediction Using Data Mining with Linear Regression and Neural Network Algorithms

Abstract

The need for housing in big cities is very high because most offices and economic centers are in big cities. Limited land and high demand cause house prices to rise. Many developers build housing on the outskirts of big cities with access to trains and toll roads to make transportation easier. Property developers compete by providing the best prices, various choices of house specifications, ease of the mortgage process, and attractive promotions such as no down payment. A house is a long-term investment whose price increases yearly, so proper analysis is needed to buy a place to live in. Several factors influence the price of a house, including location, land area, building area, building type, and so on. This research aims to create a house price prediction model using the Linear Regression Algorithm and Neural Network so that the results can be useful for property agents in predicting house sales or from the buyer's side in predicting house prices. The results of this research use the Linear Regression Algorithm RMSE 0.775, while the Neural Network Algorithm uses RMSE 0.645. From this research, modeling using the Linear Regression Algorithm has better results. Still, the Linear Regression Algorithm and Neural Network Algorithm have RMSE results that are close to accurate and have small errors.