Hybrid Artificial Intelligence HFS-RF-PSO Model for Construction Labor Productivity Prediction and Optimization

This paper presents a novel approach, using hybrid feature selection (HFS), machine learning (ML), and particle swarm optimization (PSO) to predict optimize construction labor productivity (CLP). HFS selects factors that are most predictive of CLP reduce the complexity data. Selected used as inputs for four ML models prediction. The study results showed random forest (RF) obtains better performance in mapping relationship between selected affecting CLP, compared with other three models. Finally, integration RF PSO is developed identify maximum value optimum each factor. introduces new model named HFS-RF-PSO addresses main limitation existing prediction studies, which lack capacity its respect company’s preferences, such targeted CLP. major contribution this development approach optimizing influence identifying value.