Data mining plays a pivotal role in the real estate sector, where it is extensively utilized to derive valuable insights from raw data, thereby facilitating the prediction of house prices and identification of crucial housing features. Given the profound impact of housing price fluctuations on homeowners and the market, considerable research is directed towards analyzing various factors and developing predictive models. Among the array of models investigated, Random Forest, Naive Bayes, and Multiple Linear Regression emerge as the most efficient. Moreover, spatial factors and real estate agent's involvement are pivotal in inaccurate price predictions. This study benefits developers and researchers alike, providing insights into the criteria that drive housing prices and identifying the most effective machine learning models for analysis. By understanding these factors and utilizing advanced modelling techniques, stakeholders in the real estate industry can make informed decisions that benefit both buyers and sellers.