Forecasting Analysis of the Number of AIDS Incidence in China Based on the SARIMA-SVM Combination Model
Year: 2025
Type: article
Abstract: Based on the monthly incidence data of AIDS, a SARIMA model and a SARIMA-SVM combination model are constructed to study and predict the number of cases, providing a scientific basis for the prevention and control of AIDS. The monthly incidence count data of AIDS from January 2004 to September 2023 are used as the training set, and the monthly incidence count data from October 2023 to September 2024 are used as the test set. Using R software, these two models are applied to predict the monthly incidence count of AIDS in China, and the predictions are compared with the actual values to evaluate the forecasting effectiveness of the single SARIMA model and the SARIMA-SVM hybrid model. The overall trend of AIDS incidence in China from 2004 to 2024 shows an upward trend, with certain seasonal characteristics. The root mean square error (RMSE) of the SARIMA model's forecast results is approximately 578.718, and the mean absolute percentage error (MAPE) is about 11.163%. The root mean square error (RMSE) of the SARIMA-SVM hybrid model's forecast results is approximately 45.643, and the mean absolute percentage error (MAPE) is about 0.838%. The SARIMA-SVM combination model has a good fit and prediction effect on the number of AIDS monthly incidence, and the prediction accuracy is high, which can be used to predict the month-by-month incidence data of AIDS.
Authors: Mengyao Du, Xiao Chang
Institution: Anhui University of Finance and Economics
Language: English
Field: Decision Sciences
Domain: Social Sciences
Open Access status: hybrid
OpenAlex ID: W4409379374