Teaching reform and innovation of vocational development and employment guidance courses in colleges and universities based on random forest model

Abstract

Abstract The current employment situation of graduates is serious and complicated, and employment work is very difficult. Furthermore, the employment quality of college graduates is an important reflection of the quality of education teaching and talent cultivation in higher education. Using big data to provide all-round and multi-perspective feedback on employment quality can find the direction of efforts to improve employment quality further, provide an important reference basis for schools to adjust the layout of majors, make development plans, reform education teaching, optimize career guidance courses and optimize enrollment policies and measures, and effectively promote universities to fulfill better their historical mission of serving the society. This paper extracts features for a series of school behavior data of students and carries out feature selection through appropriate methods. Specifically, the construction problem of the traditional random forest model is analyzed, and a new model is proposed by combining it with a decision tree algorithm; then, the model is constructed and adjusted by grid parameters to ensure the accuracy of the model, and finally, the model is compared and analyzed. The research shows that the accuracy of the RF prediction model using standard features is 0.702, and the LSTM prediction model using only temporal features is only 0.683. In contrast, the prediction accuracy of the model in this paper reaches 0.805. Therefore, the prediction accuracy of the model based on the decision tree algorithm is much higher than the other two, which is effective for optimizing the teaching of career development and employment guidance courses in colleges and universities, thus can improve the education and management-related to career planning and career guidance in schools.