Artificial intelligence algorithms to predict Italian real estate market prices

Purpose The assessment of the Real Estate (RE) prices depends on multiple factors that traditional evaluation methods often struggle to fully understand. Housing prices, in particular, are foundations for a better knowledge Built Environment and its characteristics. Recently, Machine Learning (ML) techniques, which subset Artificial Intelligence, gaining momentum solving complex, non-linear problems like house price forecasting. Hence, this study deployed three popular ML techniques predict dwelling two cities Italy. Design/methodology/approach An extensive dataset about is collected through API protocol North Italy, namely Brescia Varese. This data used train test most models, i.e. ElasticNet, XGBoost Neural Network, order with six different features. Findings models' performance was evaluated using Mean Absolute Error (MAE) score. results showed artificial neural network performed than others predicting MAE 5% lower second-best model (which XGBoost). Research limitations/implications All models had an accuracy drop forecasting expensive cases, probably due lack data. Practical implications accessibility easiness proposed will allow future users datasets. Alternatively, further research may implement networks, knowing they work kind task. Originality/value To date, first comparison usually employed when prices.