Article Details

Abstract

To address the issues of insufficient precision in employment guidance and inaccurate identification of students with employment difficulties in vocational undergraduate colleges, this study takes the Computer Application Technology program at a vocational college in Gansu Province (pseudonym “Y”) as an example and constructs a data mining-based precision employment assistance model. By collecting multidimensional data from 44 graduates and 510 job postings, the random forest algorithm is used to analyze factors affecting employment. It is found that academic performance (importance 0.342), type of employer (0.156), and city level of employment (0.098) are key factors influencing salary. The Apriori algorithm is employed to extract high-association rules such as “Certificate_Java/Python + GPA_Excellent → Industry_IT Services” (confidence 77.8%) and “Certificate_Software Designer → Position_Programmer/Developer” (confidence 73.3%). Using TF-IDF combined with the K-means algorithm, students are classified into four categories: all-round, academic, practical, and general. Based on the analysis results, a four-stage assistance model of “Identification—Diagnosis—Matching—Assistance” is established, and a prototype intelligent recommendation system is developed to implement personalized precision assistance, providing a replicable practical example for the digital transformation of vocational colleges.

Keywords

Data Mining; vocational undergraduate; precision employment assistance; Random Forest; Apriori algorithm; intelligent recommendation

References

1. [1] Liu Lina Graduate Employment Intelligent Recommendation System Based on Improved Apriori Algorithm [J]. Journal of Liaodong University (Natural Science Edition), 2021, 28 (2): 130-135
2. [2] Chen Shuoquan, Zhong Yintang, She Zirun, etc Employment Analysis of College Students Based on Data Mining Algorithms: A Case Study of Statistics Major at Hanshan Normal University [J]. Journal of Hanshan Normal University, 2024, 45 (3): 68-75
3. [3] Li Long, Jin Shuo, Huang Xia Research on Graduate Employment Recommendation Algorithm Based on Improved TF-IDF Algorithm [J]. Computer and Digital Engineering, 2023, 51 (9): 1985-19892118
4. [4] Zhang Yijing, Hu Xiaoyu A university employment analysis model based on data mining and Apriori algorithm [J]. Information Technology and Informatization, 2025 (8): 137-140
5. [5] Li Chuan, Liu Zhouzhou IT Professional Employment Model Based on Decision Tree Algorithm [J]. Ordnance Automation, 2023, 42 (5): 50-53, 74
6. [6] Yu Yanhua Exploration of the Application of Data Mining in Precise Employment of Vocational College Students [J]. Information and Computer (Theoretical Edition), 2023, 35 (8): 218-220
7. [7] Yang Ming, Fan Xu, Xu Haoran Research on the Application of User Interest Model and Apriori Algorithm in College Student Employment Recommendation [J]. Modern Electronic Technology, 2020, 43 (13): 119-122
8. [8] Wei Shanchun Research on the Collection of Employment Demand Information Resources Based on Data Mining [J]. Information Science, 2023, 41 (9): 130-137
9. [9] Ding Ting, Gong Zhen, Zhu Chenjie Research on the Path of High Quality Employment Training for College Students Based on Educational Data Mining in the Context of Digital Economy J. Business Economics, 2025 (2): 191-193
10. [10] Breiman L. Random Forests [J].Machine Learning，2001，45（1）：5-32.

Funding

The special project of "Career Planning and Employment Guidance for College Students" in 2025 under the "14th Five Year Plan" of Gansu Education Science "," Research on the Precision Employment Assistance Mode of Vocational Colleges and Universities Based on the Background of 'Internet plus' - Taking Gansu Y Vocational College as an Example "(GS [2025] GHBZX0087)

About the authors

Liu Xingwei (1993-), male, Han ethnicity, from Baiyin, Gansu, lecturer, master's student, research direction: big data analysis.