Graduate employability has become a central measure of higher education effectiveness, reflecting how well academic institutions prepare students for professional success. In an era of rapid technological advancement and evolving industry demands, higher education institutions are challenged to balance academic preparation and career readiness to ensure that graduates are competent, adaptable, and competitive in the workforce. This study examined how academic preparation and career readiness predict graduate employability among tertiary education graduates. Specifically, it sought to assess graduates perceived levels of academic preparation, career readiness, and employability; determine their interrelationships; establish predictive influence; and compare the predictive accuracy of various models—Linear Regression, Random Forest, and Support Vector Regression (SVR). A quantitative predictive–correlational design was employed using data from 934 graduates who completed a Graduate Satisfaction Survey (2018–2025) of the College of Computer Studies and Engineering. Descriptive statistics, Pearson correlation, multiple regression, and machine learning models were analysed using Python and Jupyter Notebook. Visualizations such as bar charts, scatter plots, heatmaps, and a 3D regression plane were used to interpret findings. Results showed that graduates rated academic preparation (M=4.31) and employability (M=4.27) as very high, and career readiness (M=4.18) as high. Academic preparation (r=0.74) and career readiness (r=0.79) both had strong, positive correlations with employability. Regression analysis revealed that the two predictors jointly explained 83% of employability variance (R2=0.83). Among the models tested, the Random Forest Regressor achieved the highest predictive accuracy (R2=0.85, MAE=0.12, RMSE=0.16). Findings confirm that academic preparation and career readiness significantly and jointly predict graduate employability. These results emphasize the importance of integrating rigorous academic instruction with structured career development initiatives to produce employable, industry-ready graduates.

• Academic Preparation
• Career Readiness
• Graduate Employability
• Predictive–Correlational Study
• Random Forest

[1] J. Andrews and H. Higson, "Graduate employability, ‘soft skills’ versus ‘hard’ business knowledge: A European study," Higher Education in Europe, vol. 33, no. 4, pp. 411–422, 2018.

[2] G. S. Becker, Human Capital: A Theoretical and Empirical Analysis, with Special Reference to Education, Chicago, IL, USA: Univ. of Chicago Press, 1964.

[3] M. Fugate and A. J. Kinicki, "Employability: A psycho-social construct, its dimensions, and applications," Journal of Vocational Behavior, vol. 65, no. 1, pp. 14–38, 2018.

[4] M. Yorke, Employability in Higher Education: What it is, What it is not, York, U.K.: Higher Education Academy, 2016.

[5] M. Yorke and P. Knight, Embedding Employability into the Curriculum, York, U.K.: Higher Education Academy, 2006.

[6] N. Sultana and M. M. Malik, "Predicting graduate employability using machine learning and data analytics," Education and Information Technologies, vol. 27, no. 5, pp. 6791–6810, 2022.

[7] S. Succi and M. Canovi, "Soft skills to enhance graduate employability: Comparing students and employers’ perceptions," Studies in Higher Education, vol. 45, no. 9, pp. 1834–1847, 2020.

[8] J. W. Creswell and J. D. Creswell, Research Design: Qualitative, Quantitative, and Mixed Methods Approaches, 5th ed., Thousand Oaks, CA, USA: Sage Publications, 2018.

[9] P. Mishra, M. Koehler, and K. Henriksen, "The 21st-century learning framework and teacher professional development: Implications for employability," Educational Technology Research and Development, vol. 68, no. 2, pp. 319–334, 2020.

[10] S. Singh, R. Kaur, and A. Sharma, "Using random forest regression for student performance prediction and employability analysis," International Journal of Emerging Technologies in Learning (iJET), vol. 17, no. 3, pp. 45–57, 2022.