This chapter explores the process of co-pyrolyzingCo-pyrolyzing biomass with plastic waste to produce bio-oil. The amount of bio-oilBio-oil generated, known as bio-oil yield (BOY), can vary significantly when plastics are added to biomass due to interactions between the two materials. However, understanding these interactions and accurately predicting BOY while considering multiple factors is complex and often limited by traditional methods. To tackle this challenge, this chapter employs a machine learning model called XGBoost, combined with a tool known as Shapley additive explanationShapley additive explanation (SHAP), to create clear and interpretable models for predicting both BOY and interaction effects during co-pyrolysis. SHAP is a method for explaining the output of any machine learning model by attributing each feature’s contribution to the final prediction, using a game-theoretic approach based on Shapley values. The models are based on 26 input features. To address imbalances in the dataset, where certain outcomes were underrepresented, a technique called synthetic minority over-sampling was applied. The XGBoost models achieved impressive accuracy, with nearly 90% for BOY predictions and over 85% for predicting interaction effects. Using SHAP, the chapter provides insights into how individual features and their interactions influence the model’s predictions. While reaction temperature and the biomass-to-plastic ratio were the most influential factors, feedstock characteristics overall contributed more than 60% to the co-pyrolysis process. These findings not only shed light on the mechanisms of co-pyrolysis but also highlight potential areas for future research and optimization. By combining machine learning with interpretability tools, this chapter offers a powerful approach to understanding and improving the co-pyrolysis process.