The global digital infrastructure is currently facing a "perfect storm" of rising cyber threats and a critical workforce shortage estimated at 4.7 million professionals. Despite the increasing output of graduates, industry research indicates that only 25–30% of engineering graduates are considered "job-ready". This sys-tematic review evaluates current trends in using Machine Learning (ML) to auto-mate student assessment and bridge the employability gap. By surveying academ-ic databases and industry reports from 2017– 2025, this paper identifies key find-ings regarding the efficacy of various classifiersspecifically Decision Trees (DT), Random Forests (RF), and XGBoost-in predicting graduate success and diagnosing technical discrepancies. The review highlights that while technical skills like programming are well-taught, significant gaps exist in Governance, Risk, and Compliance (GRC), Cloud Security, and Analytical Thinking. This study concludes that there is an urgent need for a new, specialized ML-based framework to align educational outcomes with real-time cybersecurity demands.
Rajendra et al. (Fri,) studied this question.