I. Introduction
The need to integrate Systems Dynamics (SD) with Data science (DS) is growing. While DS approaches are being developed and widely used across various topics, they are generally not accounting for the dynamic nature and complexity of systems [1]. Machine Learning (ML) techniques, for instance, are mostly variants of statistical techniques, with classification, regression and clustering models [2], ignoring the dynamic complexity of the systems studied, as well as causal relationships. SD modeling capture the feedback structures of the systems in question [3], though lacks means to analyze data in a meaningful manner. Combining both will help take advantages of those capabilities, which are critical to accurately capture complex system features and thoroughly investigate behavioral patterns for proper understanding.