House Price Prediction based on ML using Regression Techniques

Abstract

Guessing models for determining the sale price of houses in cities like Bengaluru still serve as a challenging and deceptive task. The retail price of buildings in cities such as Bengaluru depends on the number of other items. Important factors that may affect the price include the location, location and location of its facilities. In this research project, analytical research was conducted by considering a data set that is always open to the public by displaying available housing structures in the form of a machine hackathon platform. The data set has nine features. In this study, an effort has been made to develop a predictive model for price analysis based on price factors. Modeling tests use some retraction techniques such as multi-line retrieval (Small Squares), Lasso and Ridge retrieval models, vector retrieval, and reinforcing algorithms such as Extreme Gradient Boost Regression (XG Boost). Such models are used to create a predictive model and to select the most efficient model by performing comparative analysis and predictor errors found between these models. Here, the effort is to build a pricing model for price analysis based on price factors.