Open Access
Research Article
Predicting IT graduate student’s employability using machine learning and deep learning hybrid approaches
*Ankita ChopraCorresponding authorchopraankita3007@gmail.comDepartment of Engineering and Technology Jagannath UniversityJaipur, Rajasthan, 302022, IndiaView full profile → , Madan Lal Sainimadan.e13485@cumail.in; mlsaini@gmail.comDepartment of Computer Science & Engineering Apex Institute of Technology Chandigarh UniversityDepartment of Computer Science and Engineering Apex Institute of Technology Chandigarh UniversityMohali, Punjab, 140413, IndiaView full profile → , Vivek Kumar Sharmavkshere4every1@gmail.comDepartment of Engineering and Technology Jagannath UniversitySchool of Computing Science and Engineering Galgotias UniversityGreater Noida, Uttar Pradesh, 302022, IndiaView full profile →
* Corresponding author · click or hover a name for details
- Received:
- 01 Apr 2025
- Published Online:
- 01 May 2026
- Article type:
- Research Article
- Language:
- EN
- Article no.:
- JIOS-2290
- Pages:
- 1989–2001
Abstract
The growing demand for skilled professionals highlights the need for accurate prediction of employability and placement success among engineering students. Traditional methods of assessing placement success often rely on static parameters like academic percentage, written test score, interviews, and resume information. These methods fail to capture the dynamic interdependencies between academic performance, technical abilities, interpersonal skills, analytical problem-solving, critical analysis, and decision-making capabilities. This study proposes machine learning and deep learning-based approach to address these limitations, leveraging data-driven techniques to enhance prediction accuracy and also helps in identifying the important graduate feature for placement success. The proposed methodology integrates diverse datasets, including academic records, aptitude marks, soft skills assessment marks, and behavioural attributes. After data pre-processing 32 feature are taken to train and validate the proposed model. Findings reveal that the proposed model attains an 81.7% prediction accuracy, surpassing conventional approaches such as LR, RF, and GBM. Moreover, Feature importance analysis emphasizes the significance of the dominant role of specific parameters, such as technical skills and aptitude competency, in influencing employability outcomes. This study underscores the potential of machine learning and deep learning techniques in forecasting placement success based on their skills. Education institutes can identify skill gaps in students who are less likely to be placed and they can run specific training programs, workshops, or certifications to boost employability.
Keywords
Subject Classifications
68T0768T0562H30
References
[1] A. Bai and S. Hira, “An intelligent hybrid deep belief network model for predicting students employability,” Soft Comput., vol. 25, no. 14, pp. 9241–9254 (2021), doi: 10.1007/s00500-021-05850-x.[2] E. Alyahyan and D. Düştegör, “Predicting academic success in higher education: literature review and best practices,” Int. J. Educ. Technol. High. Educ., vol. 17, no. 1 (2020), doi: 10.1186/s41239-020-0177-7.[3] P. Kapil, “Bridging the Industry- Academia skill gap A conceptual investigation with special emphasis on the management education in India,” IOSR J. Bus. Manag., vol. 16, no. 3, pp. 08–13 (2014), doi: 10.9790/487x-16330813.[4] V. Krishnaiah and Y. H. Kadegowda, “Undergraduate engineering students employment prediction using hybrid approach in machine learning,” Int. J. Electr. Comput. Eng., vol. 12, no. 3, pp. 2783–2791 (2022), doi: 10.11591/ijece.v12i3.pp2783-2791.[5] N. Mezhoudi, R. Alghamdi, R. Aljunaid, G. Krichna, and D. Düştegör, “Employability prediction: a survey of current approaches, research challenges and applications,” J. Ambient Intell. Humaniz. Comput., vol. 14, no. 3, pp. 1489–1505 (2023), doi: 10.1007/s12652-021-03276-9.[6] T. Gupta, A. Singh, A. Kaushik, and B. T. Student, “Placement Predict: A Review of Engineering Graduate Placement Statistics in India,” Int. J. Eng. Sci. Comput. (2018), [Online]. Available: http://ijesc.org/[7] V. K. Gokuladas, “Predictors of employability of engineering graduates in campus recruitment drives of Indian software services companies,” Int. J. Sel. Assess., vol. 19, no. 3, pp. 313–319 (2011), doi: 10.1111/j.1468-2389.2011.00560.x.[8] K. Vinutha and H. K. Yogisha, “Prediction of employability of engineering graduates using machine learning techniques,” Proc. 2021 8th Int. Conf. Comput. Sustain. Glob. Dev. INDIACom 2021, pp. 742–745 (2021), doi: 10.1109/INDIACom51348.2021.00132.[9] S. Thavasi and T. Revathi, “A personalized machine learning–based system to evaluate students’ skillset and analyze the gap between academia and industry for engineering students,” Kybernetes (2024), doi: 10.1108/K-01-2024-0053.[10] J. Koen, U. C. Klehe, and A. E. M. Van Vianen, “Employability among the long-term unemployed: A futile quest or worth the effort?,” J. Vocat. Behav., vol. 82, no. 1, pp. 37–48 (2013), doi: 10.1016/j.jvb.2012.11.001.[11] F. F. Patacsil and C. L. S. Tablatin, “Exploring the importance of soft and hard skills as perceived by it internship students and industry: A gap analysis,” J. Technol. Sci. Educ., vol. 7, no. 3, pp. 347–368 (2017), doi: 10.3926/jotse.271.[12] Y. Wei, X. Rao, Y. Fu, L. Song, H. Chen, and J. Li, “Machine learning prediction model based on enhanced bat algorithm and support vector machine for slow employment prediction,” PLoS One, vol. 18, no. 11 (2023), doi: 10.1371/journal.pone.0294114.[13] J. Tu, A. Lin, H. Chen, Y. Li, and C. Li, “Predict the Entrepreneurial Intention of Fresh Graduate Students Based on an Adaptive Support Vector Machine Framework,” Math. Probl. Eng., vol. 2019 (2019), doi: 10.1155/2019/2039872.[14] A. Qostal, A. Moumen, and Y. Lakhrissi, “CVs Classification Using Neural Network Approaches Combined with BERT and Gensim: CVs of Moroccan Engineering Students,” Data, vol. 9, no. 6 (2024), doi: 10.3390/data9060074.[15] Y. Zayed, Y. Salman, and A. Hasasneh, “A Recommendation System for Selecting the Appropriate Undergraduate Program at Higher Education Institutions Using Graduate Student Data,” Appl. Sci., vol. 12, no. 24 (2022), doi: 10.3390/app122412525.[16] Y. Singh, M. Saini, and Savita, “Impact and Performance Analysis of Various Activation Functions for Classification Problems,” Proc. IEEE InC4 2023 - 2023 IEEE Int. Conf. Contemp. Comput. Commun. (2023), doi: 10.1109/InC457730.2023.10263129.[17] A. Chopra and M. Lal Saini, “Comparison Study of Different Neural Network Models for Assessing Employability Skills of IT Graduates,” Int. Conf. Sustain. Commun. Networks Appl. ICSCNA 2023 - Proc., pp. 189–194 (2023), doi: 10.1109/ICSCNA58489.2023.10368605.[18] M. L. Saini, R. S. Telikicharla, Mahadev, and D. C. Sati, “Handwritten English Script Recognition System Using CNN and LSTM,” Proc. InC4 2024 - 2024 IEEE Int. Conf. Contemp. Comput. Commun. (2024), doi: 10.1109/InC460750.2024.10649099.[19] A. Chopra and M. L. Saini, “Neural Network Based Employability Index for IT Graduates,” Commun. Comput. Inf. Sci., vol. 2268 CCIS, pp. 118–127 (2025), doi: 10.1007/978-3-031-75167-7_9.[20] A. Chopra, “Employability Prediction Dataset,” GitHub (2024). Available: https://github.com/ankit737257/employability-dataset[21] A. Sharma and R. Gupta, “Machine learning techniques for student performance prediction,” Journal of Statistics and Management Systems, vol. 24, no. 5, pp. 1123–1135 (2021).[22] P. Verma and S. K. Singh, “Data-driven approaches in educational analytics,” Journal of Information and Optimization Sciences, vol. 43, no. 2, pp. 567–580 (2022).[23] R. Mehta and M. Singh, “Artificial intelligence in higher education systems,” Journal of Statistics and Management Systems, vol. 25, no. 3, pp. 789–802 (2022).[24] S. Agarwal and M. Jain, “Predictive modelling using neural networks,” Journal of Information and Optimization Sciences, vol. 42, no. 6, pp. 1345–1358 (2021).[25] K. Singh and A. K. Singh, “Optimization techniques in machine learning applications,” Journal of Statistics and Management Systems, vol. 23, no. 4, pp. 945–960 (2020).
Views: 51Downloads: 7Citations: 0
