Abstract

Nowadays, people view homes as an investment strategy rather than just a place to live. To increase house equity, accurate housing price forecasting is crucial. House price fluctuations in the real estate market are caused by the effects of other features that are correlated to housing prices.

This research examined and investigated house payment data obtained from the UK land registry in order to more effectively and properly assess house pricing. In this study, an effort has been made to develop a predictive model for evaluating the price based on price-influencing variables. Modelling explorations use boosting algorithms like Extreme Gradient Boost Regression (XG Boost) as well as regression techniques like Linear Regression, Decision Tree, and Random Forest models. By performing a comparative study on the prediction errors obtained between various models, the models were utilized to construct a predictive model and select the best-performing model. Here, an effort was made to build a predictive model for evaluating the price based on those characteristics.

The outcomes of the experiment demonstrate that XGboost has the highest prediction accuracy, with a prediction accuracy score of 0.90. The XGboost algorithm performs better at generalization and resilience in data prediction than linear regression and decision tree models, and it also guards against overfitting.

House Price Predictive System