Experimental determination of thermochemical conversion characteristics of multi-source organic solid wastes is a time-consuming and labor-intensive process. By leveraging machine learning methods, the correlation mechanism between different feedstock properties and thermochemical characteristics can be explored to enable fast and accurate prediction. A comprehensive dataset was constructed based on the fundamental properties and pyrolysis characteristics of 38 types of industrial organic solid waste. Descriptive statistical analysis, correlation analysis, and principal component analysis (PCA) were employed to uncover patterns within the dataset. Subsequently, the random forest (RF), gradient boosting decision tree (GBDT), and extreme gradient boosting (XGBoost) algorithms were utilized to predict the high heating value (HHV) of organic solid waste, the distribution of fast pyrolysis products, and the thermogravimetric curves under various atmospheres. The R^2 values achieved for HHV, product distribution, and thermogravimetric curves ranged from 0.835 to 0.866, 0.701 to 0.875, and 0.976 to 0.980, respectively. Additionally, the Mean Decrease Impurity (MDI) and SHapley Additive exPlanations (SHAP) methods were applied to analyze the model′s performance and identify key features influencing the model′s decision-making process. This allowed for explaining the relationship between feedstock properties and HHV. It also enabled explaining the connection between product distribution and pyrolysis characteristics. This study aims to offer valuable insights into the intelligent management and efficient disposal of organic solid waste.