This study presents an optimal house price prediction algorithm using XGBoost. The research compares various machine learning models, including linear regression, multilayer perceptron, random forest, support vector regressor, and XGBoost, to determine the most effective model for predicting house prices. The dataset used is from the Ames City housing market in Iowa, USA. The results show that XGBoost outperforms other models in terms of accuracy, with an R-squared value of 0.93 and a mean squared error (MSE) of 0.001. XGBoost is also effective in identifying key factors influencing house prices, such as overall house quality, ground floor living area, garage cars, and total basement square footage. The study emphasizes the importance of hyperparameter tuning for improving model performance and highlights the significance of feature importance in house price prediction. The findings suggest that XGBoost is the best model for house price prediction, offering accurate and interpretable results. The study also discusses the limitations of the research, including data availability, and suggests future directions for expanding the scope of the study. The results provide valuable insights for real estate professionals, investors, and potential homebuyers, enabling more informed decision-making in the housing market.This study presents an optimal house price prediction algorithm using XGBoost. The research compares various machine learning models, including linear regression, multilayer perceptron, random forest, support vector regressor, and XGBoost, to determine the most effective model for predicting house prices. The dataset used is from the Ames City housing market in Iowa, USA. The results show that XGBoost outperforms other models in terms of accuracy, with an R-squared value of 0.93 and a mean squared error (MSE) of 0.001. XGBoost is also effective in identifying key factors influencing house prices, such as overall house quality, ground floor living area, garage cars, and total basement square footage. The study emphasizes the importance of hyperparameter tuning for improving model performance and highlights the significance of feature importance in house price prediction. The findings suggest that XGBoost is the best model for house price prediction, offering accurate and interpretable results. The study also discusses the limitations of the research, including data availability, and suggests future directions for expanding the scope of the study. The results provide valuable insights for real estate professionals, investors, and potential homebuyers, enabling more informed decision-making in the housing market.