An Explainable AI Framework with ML Model Stacking for House Price Prediction

The post-COVID-19 real estate market has presented challenges in finding affordable housing. Accurate house price prediction systems can aid in addressing this issue. This research develops a stacking regression model framework for improving predictive performance with the consideration of Explainable AI (XAI) of house price estimation. This new model was subsequently compared to Regression-based prediction models and a Neural Network to assess model performance. The Stacking Regressor’s strong $r^{2}$ value of 0.901 and its noticeably lower MAE and RMSE highlight strong precision. XAI techniques, particularly SHAP values, were employed to enhance model interpretability, offering insights into individual feature contributions.