The number of unemployed computer science graduates has increased significantly over the last few years. The primary reason for this problem is the skill gap between the graduates and what is required on the job market. The current study aims to address the challenge of aligning the skills of computer science graduates with the evolving demands of the job market. To achieve this objective, the current research leverages Machine Learning (ML) and Deep Learning (DL) techniques to predict the skills required by employers and those possessed by graduates. The dataset used in this study has been carefully curated and annotated by experts in the field. It entails 18 features that capture various aspects of a graduate’s skillset, such as programming languages, technical expertise, and soft skills. Additionally, the dataset includes information on the most common job positions in the computer science industry (i.e. a total of 8 roles). A sample size of 3,831 computer science graduates was sourced from alumina surveys and reputable hiring agencies. The dataset provides a comprehensive view of the skills landscape in the computer science domain. Several ML classifiers, ensemble methods, and DL approaches were utilized in a series of experiments. The correlations and important skills and jobs in the market were given focus. The experimental results indicate that support vector machines and neural networks achieved high accuracies of 82% and 88%, respectively. By analyzing the results, this study seeks to uncover patterns and trends that can guide the development of educational programs and curricula, ensuring they are aligned with the evolving needs of the industry.