Investigating the Effectiveness of Machine Learning Techniques for Real Estate Price Prediction

In the real-estate industry, the capacity to extract significant information from raw data makes it extremely valuable for predicting home values, housing attributes, and much more. The cost of housing varies from day to day and is frequently increased arbitrarily rather than using calculations. The housing market and homeowners are routinely impacted by changes in property values. A literature study is done to evaluate the most important factors and reliable models for predicting housing values. The results of this analysis confirmed the use of Support Vector Regression, Linear Regression, and Artificial Neural Networks as the most effective models when compared to others. Furthermore, our data imply that geographical and real estate agents are important determinants in forecasting property values. This research will be very helpful in determining the most important variables for estimating housing costs and the best machine learning model to employ when doing this type of research, especially for academics and housing developers.