Simulation Research on College Students’ Employment Prediction Model Based on Decision Tree Classification Algorithm

The policy of expanding higher education enrollment has significantly boosted the annual count of college graduates. However, their employment prospects remain challenging. The employment rate among these graduates plays a pivotal role in balancing the human resources market. Using statistical regression theory as a foundation, this study examines the factors impacting the employment rate of college graduates and quantifies the influence of these factors. This analysis lays the groundwork for the establishment of a precise system to predict the employment rate of college graduates. Often, college students' self-perception of their abilities diverges from the hiring criteria set by businesses. This mismatch leads many new graduates to pursue high-paying positions while overlooking more suitable opportunities at ordinary enterprises. Therefore, accurate assessments of graduates' employability and realistic salary expectations are crucial. Leveraging data mining concepts, this paper explores the evaluation and application of an Employment Physical Education Model (EPM) for university students. It delves into the predictive accuracy of the EPM and identifies its influencing factors. Furthermore, the study utilizes the EPM to assess the employment landscape for graduates and offers informed recommendations and decision-making frameworks to enhance university student employment outcomes.