Implementing Neural Networks Within Portfolio Management to Support Decision-Making Processes

Faced with rapidly changing technologies, diminishing product life cycles and heightened global competition, portfolio managers across all industries encounter increasing challenges within decision-making processes. While portfolio decisions were based on subjective experience in the last decades, this is no longer sufficient. Nowadays, as complexity grows constantly, sophisticated analytical methods are needed to enable effective decisions in portfolio management. However, when regarding the field of portfolio management, one can detect a deficit in the amount of research concerning the usage of analytical methods. Additionally, there is a gap between a company's capacity to produce analytical results and its ability to apply them effectively to portfolio management issues. This paper promotes a methodology that uses a neural network to model potential correlations among portfolio-relevant corporate key performance indicators and predict future trends for these indicators. This allows companies to anticipate their portfolio's future development and to proactively manage their portfolio. The method is applied using a case study.