Graduate employability is a crucial facet within this unemployment context. Traditionally, an individual's employability has primarily hinged on their academic performance, typically measured by their Cumulative Grade Point Average (CGPA). However, recent research has unveiled that CGPA alone does not exclusively determine graduate employability; various other factors influence an individual's job prospects. The primary objective is determining suitable machine learning algorithms to predict graduates’ employment status based on factors. This study used data spanning 10 years (2012 to 2022) obtained from the Malaysia Ministry of Higher Education graduate’s tracer study. Four classification algorithms—Decision Tree, Naïve Bayes, Random Forest and Logistic Regression were employed and compared to determine the most effective model. The findings indicate that the Random Forest classifier yields the highest accuracy, initially at an average of 75%, while Logistic Regression was the 2nd best model. This study has managed to analyze 13 factors that impact graduate employment status. Important factors include Types of Higher Learning Institution and language proficiency (Bahasa Melayu and English). In addition, it is learned ICT skills is also relevant in determining whether a graduate will be working or not six months after graduating. Consequently, the insights from this study can assist higher learning institutions in Malaysia in better preparing their graduates with the requisite skills for a successful transition into the job market. Hence, data analytics enables the development of adaptive knowledge management systems that enhance the efficiency of knowledge dissemination.