Metropolitan City House Price Prediction

In this paper, we are predicting the sale price of the houses using various machine learning algorithms. Housing sales price are determined by numerous factors such as area of the property, location of the house, material used for construction, age of the property, number of bedrooms and garages and so on. This paper uses machine learning algorithms to build the prediction model for houses. Here, machine learning algorithms such as logistic regression and support vector regression, Lasso Regression technique and Decision Tree are employed to build a predictive model. We have considered housing data of 3000 properties. Predictive models for deciding the sale price of houses in metropolitan cities is still remaining as more challenging and trickier task. The sale price of properties in cities like Bengaluru depends on a variety of interdependent factors. Key factors which may affect the house price include area of the property, location of the property and its amenities. In this system, an attempt has been made to construct a predictive model for evaluating the price based on the factors that affect the price. Modelling study apply some supervised learning techniques such as Bayesian classifier or KNN algorithms. Such models are used to build a predictive model, and to pick the best performing model by performing a comparative analysis on the predictive errors obtained between these models. Here, the attempt is to construct a predictive model for evaluating the price based on factors that affects the price. We build this concept as real time application useful for real estate business and also buyer and sellers.