The conversion of waste plastics into oil and syngas through pyrolysis offers an efficient means of recycling and reusing these plastics. The types of feedstock and operational parameters in pyrolysis reactions can significantly influence the process, necessitating quantitative research. Moleculal sieve catalysts are widely employed in plastic pyrolysis due to their enhancement of the yield of desired products. However , the complex nature of the pyrolysis reaction mechanism and the associated high experimental costs pose challenges. A machine-learning approach was applied to utilize data from non-catalytic and molecular sieve catalytic processes and to build a model for analyzing raw material pyrolysis. The Gradient Boosting Regression (GBR) algorithm has the best fitting performance for predicting oil yield (R^2=0.91, RMSE=7.78), while the adaptive boosting algorithm (AdaBoost) has the bestfitting perfomance for predicting gas yield (R^2=0.83, RMSE=6.42), enabling accurate prediction of reaction conditions. It was found that optimal oil yield occurred at a heating rate of approximately 20 ℃/min and a temperature of 500 ℃ through importance ranking and single dependency analyses. Additionally, a dual dependency analysis of oil yield with reaction temperature, heating rate, and reaction time was conducted. This study quantified the effects of heating rate, pyrolysis temperature and other reaction conditions on the oil and gas yield of plastic pyrolysis, which provides a theoretical basis for the production practice of waste plastic recycling.