Abstract for: System Dynamics and Machine Learning Combined Approach to Simulate Sustainable Competitive Advantage in Banking Industry

The dynamic growth behavior of low-interest funding is a significant factor that contributes to the performance of the banking industry and its sustainability in the long term. As financial intermediary institutions, Banks must be able to manage the funding effectively and efficiently while ensuring continuous growth. Bank is a complex system consisting of feedback loops and produces dynamical behaviors, which may lead to an unfavored situation such as underperformance of profitability and limit growth. Managing the limits to growth of low-interest funding that supports the credit growth is a significant capability to obtain a sustainable competitive advantage. This capability is considered as a rare internal resource-based factor that can be achieved using simulation modelling to predict the outcome based on several intervention scenarios and overcome bounded rationality in strategy development. System dynamics and machine learning have been selected as combined approaches to simulate the dynamical behaviors. This research concluded that machine learning is necessary to validate the causal relationships of a complex system in system dynamics model using historical data pattern analysis. Furthermore, the simulation proved that to maintain a sustainable competitive advantage, it is necessary to tune the speediness of credit growth with the ability to manage low-interest funding.