An intelligent decision support approach for quantified assessment of innovation ability via an improved BP neural network

In today's competitive and changing social environment, innovation and entrepreneurial ability have become important factors for the successful development of college students. However, relying solely on traditional evaluation methods and indicators cannot comprehensively and accurately evaluate the innovation and entrepreneurial potential and ability of college students. Therefore, developing a comprehensive evaluation model is urgently needed. To address this issue, this article introduces machine learning methods to explore the learning ability of subjective evaluation processes and proposes an intelligent decision support method for quantitatively evaluating innovation capabilities using an improved BP (Back Propagation) neural network. This article first introduces the current research status of evaluating the innovation and entrepreneurship ability of college students, and based on previous research, it has been found that inconsistent evaluation standards are one of the important issues at present. Then, based on different BP models and combined with the actual situation of college student innovation and entrepreneurship evaluation, we selected an appropriate input layer setting for the BP neural network and improved the setting of the middle layer (hidden layer). The identification of output nodes was also optimized by combining the current situation. Subsequently, the conversion function, initial value and threshold were determined. Finally, evaluation indicators were determined and an improved BP model was established which was validated using examples. The research results indicate that the improved BP neural network model has a low error rate, strong generalization ability and ideal prediction effect which can be effectively used to analyze problems related to intelligent evaluation of innovation ability.