Abstract for: An integrated approach of system dynamics modeling and machine learning

The emerging trend of new technology usage presents exponential data growth in various domains across industry and academia. With the need for time and cost-efficient strategies, machine learning has emerged as the method of choice for developing applications. Machine learning applications can be seen not only in the computer science domain but also across a range of domains from finance, logistics, biology, cosmology, health care, to social sciences. The rise of machine learning as a method to explore correlations in multidimensional data provides a remarkable opportunity in this regard. However, handling unstructured and multivariate data is still time and cost-consuming and the chances of going in the wrong direction with the analysis process are still high. This challenge is where system dynamics modeling could provide a good starting point for machine learning through its participatory method that facilitates the involvement of stakeholders and experts in developing conceptual or computational models. In this work-in-progress paper, we present an integrated approach that combines machine learning with system dynamics as complementary methods that aims to provide a potentially enhanced modeling process and efficient data analysis process.