Forecasting innovation performance via neural networks—a case of Taiwanese manufacturing industry

Abstract In the ‘knowledge economies’ era, most managers have discovered that technology can be considered as the key asset in sustaining the competitive advantage of their corporations. Many researchers have tried to discuss the relationships between technological performance and other influential factors, such as strategic management, information resources, etc. But they do not mention the issues concerning how each dimension influences innovation performance and how to forecast innovation performance based on these dimensions. This study presents a forecasting model that predicts innovation performance using technical informational resources and clear innovation objectives. Specifically, we propose a neural network approach, which utilizes the Back-Propagation Network (BPN) to solve this problem. Also we examine the results and compare them to those attained using the statistical regression method. The result shows that the BPN method outperforms the statistical regression method as far as forecasting performance concerned. With this method, a decision maker can predict innovation performance and adjust allocated resources to match his/her company's innovation objectives.