Talent Cultivation of New Ventures by Seasonal Autoregressive Integrated Moving Average Back Propagation Under Deep Learning

Abstract

This study combines the discovery methods and training of innovative talents, China's requirements for improving talent training capabilities, and analyses the relationship between the number of professional enrollments in colleges and universities and the demand for skills in specific places. The research learns the characteristics and training models of innovative talents, deep learning (DL), neural networks, and related concepts of the seasonal difference Autoregressive Moving Average (ARMA) Model. These concepts are used to propose seasonal autoregressive integrated moving average back propagation (SARIMA-BP). Firstly, the SARIMA-BP artificially sets the weight parameter values and analyzes the model's convergence speed, superiority, and versatility. Then, particle swarm optimization (PSO) algorithm is used to pre-process the model and test its independence. The accuracy of the model is checked to ensure its proper performance. Secondly, the model analyzes and predicts the relationship between the number of professional enrollments of 10 colleges and universities in a specific place and the talent demand of local related enterprises. Moreover, the established model is optimized and tested by wavelet denoising. Independent testing is done to ensure the best possible performance of the model. Finally, the weight value will not significantly affect the model's versatility obtained by experiments. The prediction results of professional settings and corporate needs reveal that: there is a moderate correlation between professional locations and corporate needs; colleges and universities should train professional talents for local enterprises and eliminate the practical education concepts.