Raziyeh Moghaddas; Farinaz Tanhaei; Maryam Al Moqbali; Solmaz Safari
Abstract
The incorporation of machine learning (ML) approaches into business intelligence (BI) results in a great impact on fields that require predictive analysis, such as the real estate market. An accurate prediction of housing prices can provide benefits to stakeholders such as developers, investors, and ...
Read More
The incorporation of machine learning (ML) approaches into business intelligence (BI) results in a great impact on fields that require predictive analysis, such as the real estate market. An accurate prediction of housing prices can provide benefits to stakeholders such as developers, investors, and policy planners. This study aims to explore the application of ML techniques to property valuation by creating a dataset based on real-world house price data collected from various areas in Muscat, Oman. Several ML models, including Linear Regression, Ridge Regression, Gradient Boosting, Random Forest, and Support Vector Regression, were applied and examined on the created dataset to estimate the house prices. Besides, hyperparameter tuning is used for each model in order to improve their predictive accuracy. Finally, we assessed the performance of each model using standard evaluation metrics, i.e., Mean Absolute Error (MAE), Mean Squared Error (MSE), and the R-squared (R²) score. The findings of this research work provide a comparative analysis of model efficiency that highlights both the capabilities and limitations of each model. This study demonstrates the practical power of ML techniques in real-state analytics and its wider applicability in improving BI systems subsequently.
