Singapore House Price Forecasting Using Machine Learning

Real estate valuation, particularly predicting house prices, is a critical aspect of the real estate industry. This paper provides a comprehensive overview of the application of various machine learning models for predicting house expenses. Four distinct models are evaluated: Back Propagation neural network (BP), random forest (RF), seagull optimization algorithm (SOA), and lion swarm optimization-based algorithm (SLSO-BP). This research aims to identify the most effective machine learning algorithm for accurately predicting house prices, utilizing the mean square error (MSE) and R-squared (R2) as the evaluation metric. Through a comparative analysis, our findings reveal that the SLSO-BP algorithm demonstrates superiority over other predictive tools, showcasing the lowest MSE. This study contributes to the advancement of predictive modeling in real estate, offering valuable insights for practitioners, researchers, and policymakers involved in housing market analysis and decision-making.