Over the last few years, researchers have shown a growing interest in polyvinyl chloride (PVC) gasification and have conducted several studies to evaluate and enhance the process. These studies have recognized that processing parameters have a crucial impact on the assessment of PVC gasification. Despite this, there has been limited exploration of the use of machine learning techniques, particularly regression models, to optimize PVC waste gasification. This study aims to investigate the effectiveness of regression models as machine learning algorithms in predicting the performance of PVC waste gasification. The study uses data collected through a validated thermodynamic model, and three different regression models are tested and compared in detail. Cold gas efficiency and normalized carbon dioxide emission are predicted using linear, quadratic, and quadratic with interaction algorithms. The outcomes for emission algorithms reveal that the linear emission algorithm possesses a high R-square value of 97.49%, which indicates its strong predictive capability. Nevertheless, the quadratic algorithm outperforms it, exhibiting an R-square value of 99.81%. The quadratic algorithm with an interaction term, however, proves to be the best among them all, displaying a perfect R-square value of 99.90%. A similar observation is detected for the cold gas efficiency algorithms. These findings suggest that the quadratic algorithm with an interaction term is superior and has a greater predictive accuracy. This research is expected to provide valuable insight into how regression algorithms can be used to maximize the efficiency of PVC waste gasification and reduce its associated environmental concerns.