A Study on the Time Series Prediction of the Number of Foreign Students Using Machine Learning

The purpose of this study is to analyze the structural patterns of international student inflow and predict future trends using the ARIMA model. By employing data from 2010 to 2023 on international students in South Korea, the study ensures stationarity through differencing and identifies the optimal ARIMA(2, 1, 1) configuration via ACF and PACF analyses. Results highlight the significant impact of external shocks, such as the COVID-19 pandemic, on student enrollment trends, followed by a gradual recovery. The study also identifies key factors influencing student attraction and retention, including nationality, gender, degree type, language proficiency, and educational satisfaction. Moreover, the research incorporates multivariate analysis, offering insights into the role of tailored support programs such as language education, cultural adaptation services, and academic assistance. These findings provide practical recommendations for enhancing recruitment strategies and underline South Korea's potential to strengthen its position as a global educational hub through data-driven policymaking and strategic planning..