Project control is a pivotal element within management frameworks, with Earned Value Management (EVM) standing as one of the most popular methodologies. Recent advancements, such as the Triad Method, have extended EVM’s applicability to stochastic conditions by incorporating Monte Carlo simulations and machine learning models. This study delves into the potential of Explainable Boosting Machines (EBM), an interpretable machine learning method, within the context of the Triad Method. Preliminary results from a simple case study highlight EBM’s ability to complement interpretations provided by SHAP values, also recently proposed, and demonstrate superior or equivalent performance to other machine learning models. However, more research is required to generalise these findings to more complex project environments.