With the development of higher education in full swing, the number of college students in China is increasing, the employment pressure of college students is increasing, and the employment situation in universities is not optimistic. Subjective career obstacles are obstacles that individuals may encounter when they perceive themselves according to their own conditions and surrounding environmental factors based on their future career pursuit and goals. In this paper, it is of practical significance to use the employment confidence index of college students to analyze and predict their employment confidence. Based on DL (deep learning), a model GM-BPNN (Gray model-BP neural network) of subjective employment obstacles of college students and its predictive factors is proposed. Initially, the employment data of a university are collected and normalized. Then, GM and BPNN are used to model and predict the number of college students’ employment from different angles. Finally, the weights of the prediction results of GM and BPNN are determined, and the final prediction results of the number of college students’ employment are obtained by weighting. The results show that the relative error of the combined model is smaller and the accuracy is higher.