基于集成学习与关联规则算法的毕业生就业分析
Employment Analysis of Graduates Based on Ensemble Learning and Association Rules Algorithms

本文针对H学院数学与应用数学(师范)专业2020至2022届的684名毕业生的就业数据与大学四年学业成绩等数据，采用集成学习-AdaBoost回归分析以及关联规则等方法，使用Python软件对大学毕业生就业情况及其影响因素进行了详细的分析。研究结果表明，学生专业成绩对初次就业薪酬水平的影响最为显著，尤其是核心课程成绩对薪酬的影响。这一发现，验证了学业成绩与就业竞争力之间具有正相关性的结论。另外，根据数据分析的结论，本文还发现就业时间和地点、学生性别、学生生源地等因素也会对大学生的初次就业薪酬水平产生影响。综合而言，本文的分析结果为具有数学与应用数学专业的学校人才的培养提供了一些建议，学校可以根据这些发现，优化课程设置，提升学生的就业竞争力。
This study examines the data of employment and four-year college academic performance of 684 college graduates who majored in Mathematics and Applied Mathematics (Teacher Training) at H University from the classes of 2020 to 2022, utilizes ensemble learning-AdaBoost regression and association rules to investigate in detail the employment of college graduates and their influencing factors by using Python software. The results of the study indicate that academic performance, particularly in core courses, has the most significant impact on initial employment salary level. This finding provides empirical evidence for a positive relationship between academic performance and employment competitiveness. In addition, based on the findings of the data analysis, this paper also found that factors such as employment time and location, students’ gender, and students’ places of origin also have an impact on college students’ initial employment salary level. Taken together, the results of the analysis in this study provide some suggestions for the cultivation of talents in schools with majors in Mathematics and Applied Mathematics, and the schools can optimize their curricula based on these findings to enhance the employment competitiveness of their students.