The conversion of waste plastics into oil (aviation fuel) and syngas (carbon monoxide and hydrogen) through pyrolysis offers an efficient means of recycling and reusing these plastics. Factors such as feedstock types and working conditions have an important impact on pyrolysis products, which makes the reaction mechanism of pyrolysis process more complex, so it is necessary to explore the reaction nature through a large number of experimental data, and the experimental cost is high. Machine learning has the advantages of large data processing volume and easy extraction of statistical laws, which can reduce costs and research difficulties. 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 best fitting performance 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.