To optimize employment matching in colleges and universities, a hybrid bidirectional model was designed to recommend suitable companies to graduates and vice versa. First, the resume submission records of graduates and interview invitation data from enterprises were integrated to construct a sparse matrix, and K-means clustering was applied to fill missing values and mitigate data sparsity. Resumes and recruitment texts were analyzed using a latent Dirichlet allocation (LDA) topic model, combined with TF-IDF weighting, to generate a graduate–enterprise feature vector space. By dynamically weighted fusion of collaborative filtering (CF) similarity and topic model similarity, a hybrid recommendation coefficient was obtained to achieve efficient bidirectional recommendation. Experimental results revealed that the CF-LDA model constructed with weight coefficients (M=0.45 and N=0.55) significantly improved recommendation performance: the overlap rate between graduate resumes and enterprise recommendations reached 92%, the overlap rate between enterprise interview invitations and recommended talents reached 96%, and user activity increased by more than threefold (graduates and enterprises spent 65 and 141 min online per day, respectively). Compared with a single CF or LDA model, its recall rate increased by 18%–28% and the RMSE reduced by 23%–45% on publicly available datasets such as MovieLens 10M, verifying the effectiveness and generalization ability of the model. The data results indicate that the research model provides effective employment recommendation information for graduates and enterprises, improving the efficiency of graduates’ job search and enterprise recruitment.

1. [1] N. Nabulsi, B. Mcnally, and G. Khoury, “Improving graduateness: Addressing the gap between employer needs and graduate employability in Palestine,” Education + Training, Vol.63, No.6, pp. 947-963, 2021. https://doi.org/10.1108/ET-06-2020-0170
2. [2] O. Gavrylenko and V. Dvornyk, “Application of clustering methods to determine the areas of activity of candidates in recruitment for IT-companies,” System Technologies, Vol.3, No.134, pp. 126-134, 2021 (in Ukrainian). https://doi.org/10.34185/1562-9945-3-134-2021-14
3. [3] F. Wang, Y. Wen, T. Guo, J. Liu, and B. Cao, “Collaborative filtering and association rule mining-based market basket recommendation on spark,” Concurrency and Computation: Practice and Experience, Vol.32, No.7, Article No.e5565, 2020. https://doi.org/10.1002/cpe.5565
4. [4] K.-H. Cheng, “Use of real-life imagery and words in luxury brand trademarks: A study of the trademark lawsuits involving the Polo/Lauren Company,” Asia Pacific J. of Marketing and Logistics, Vol.35, No.3, pp. 606-624, 2023. https://doi.org/10.1108/APJML-10-2020-0703
5. [5] C. Weisser et al., “Pseudo-document simulation for comparing LDA, GSDMM and GPM topic models on short and sparse text using Twitter data,” Computational Statistics, Vol.38, No.2, pp. 647-674, 2023. https://doi.org/10.1007/s00180-022-01246-z
6. [6] A. Guo, “Geometric average weakening buffer GM(1,1) and its application in prediction of employment rate of college graduates,” IEEJ Trans. on Electrical and Electronic Engineering, Vol.17, No.7, pp. 1370-1371, 2022. https://doi.org/10.1002/tee.23627
7. [7] Y. Lin, “Understand the particularity of graduates and do a good job in higher vocational employment service,” Psychology Research, Vol.11, No.9, pp. 404-407, 2021. https://doi.org/10.17265/2159-5542/2021.09.004
8. [8] J. Yang, F. Ding, J. Sun, and Y. Deng, “Delayed employment among college students in Guangdong – Taking Shenzhen University as an example,” J. of Contemporary Education Research, Vol.6, No.1, pp. 29-33, 2022. https://doi.org/10.26689/jcer.v6i1.2908
9. [9] X. Li and L. Wei, “Personalized recommendation strategy and algorithm optimization on cloud computing platform,” Int. J. of Performability Engineering, Vol.14, No.10, pp. 2492-2503, 2018. https://doi.org/10.23940/ijpe.18.10.p25.24922503
10. [10] C. Iwendi, E. Ibeke, H. Eggoni, S. Velagala, and G. Srivastava, “Pointer-based item-to-item collaborative filtering recommendation system using a machine learning model,” Int. J. of Information Technology & Decision Making, Vol.21, No.1, pp. 463-484, 2022. https://doi.org/10.1142/S0219622021500619
11. [11] J. Zeng, X. He, F. Li, and Y. Wu, “A recommendation algorithm for point of interest using time-based collaborative filtering,” Int. J. of Infomation Technology and Management, Vol.19, No.4, pp. 347-357, 2020. https://doi.org/10.1504/ijitm.2020.110242
12. [12] S. Chen, L. Huang, Z. Lei, and S. Wang, “Research on personalized recommendation hybrid algorithm for interactive experience equipment,” Computational Intelligence, Vol.36, No.3, pp. 1348-1373, 2020. https://doi.org/10.1111/coin.12375
13. [13] S.-T. Park and C. Liu, “A study on topic models using LDA and Word2Vec in travel route recommendation: Focus on convergence travel and tours reviews,” Personal and Ubiquitous Computing, Vol.26, No.2, pp. 429-425, 2022. https://doi.org/10.1007/s00779-020-01476-2
14. [14] S. Wang and L. Niu, “A deep reinforcement learning recommendation model based on long and short term interest,” Computer Science and Application, Vol.13, No.5, pp. 1037-1043, 2023 (in Chinese). https://doi.org/10.12677/CSA.2023.135101
15. [15] X. Liang et al., “Hybrid Gaussian network intrusion detection method based on CGAN and E-GraphSAGE,” Instrumentation, Vol.11, No.2, pp. 24-35, 2024. https://doi.org/10.15878/j.instr.202400165
16. [16] H. T. Duong, V. H. Ho, and P. Do, “Fact-checking Vietnamese information using Knowledge Graph, Datalog, and KG-BERT,” ACM Trans. on Asian and Low-Resource Language Information Processing, Vol.22, No.10, Article No.240, 2023. https://doi.org/10.1145/3624557
17. [17] N. Kumari and P. Singh, “Automated Hindi text summarization using TF-IDF and text rank algorithm,” J. of Critical Reviews, Vol.7, No.17, pp. 2547-2555, 2020.
18. [18] H. Yu, Y. Ji, and Q. Li, “Student sentiment classification model based on GRU neural network and TF-IDF algorithm,” J. of Intelligent & Fuzzy Systems: Applications in Engineering and Technology, Vol.40, No.2, pp. 2301-2311, 2021. https://doi.org/10.3233/JIFS-189227
19. [19] R. B. Salem, E. Aimeur, and H. Hage, “A multi-party agent for privacy preference elicitation,” Artificial Intelligence and Applications, Vol.1, No.2, pp. 82-89, 2023. https://doi.org/10.47852/bonviewAIA2202514
20. [20] Y.-L. Qi et al., “Optimal feature selection based on discrete grasshopper optimization algorithm and K-nearest neighbor classifier,” Engineering Letters, Vol.32, No.1, pp. 89-100, 2024.
21. [21] S. R. Bhat, R. Bhat, and S. G. Bhat, “A comprehensive analysis of total and semi-total graphs,” Engineering Letters, Vol.32, No.1, pp. 21-29, 2024.
22. [22] M. M. Motheogane and A. B. Pretorius, “Alignment of information technology and strategic business objectives,” Proc. of the Int. MultiConf. of Engineers and Computer Scientists 2021, pp. 55-58, 2021.