Prediction of the Number of Postgraduate Entrance Examination Applicants Based on LSTM and Statistical Analysis Method

In recent years, with the expansion of higher education institutions year by year, the total number of fresh undergraduates has been rapidly increasing. This paper proposes a prediction algorithm for the number of undergraduates who will enter graduate school through long short-term memory (LSTM) based on the current development trend of graduate school and the number of admissions to graduate school in recent years.Firstly, the parameters that have the greatest influence on the prediction of the number of applicants for the examinations are statistically analyzed, and then a deep learning prediction model based on LSTM is built to predict the number of applicants for the examinations, and the results are displayed in the visualization interface. The experimental results show that the trained LSTM model works better than the Support Vector Machine (SVM) results. The prediction model will be provided to students before registering for the exam, which is of practical significance to facilitate students to make reasonable decisions.