Methodology for predicting the demand for university graduates using data mining techniques

The purpose of this research is to develop and validate an integrated methodology for predicting the demand for university graduates in a regional labor market by applying data-mining tools and machine-learning techniques. Employment monitoring data from Turgenev Orel State University for 2022–2024 served as the empirical basis. The Random Forest algorithm was used to forecast graduate employment rates across aggregated fields of study, while the K-means clustering method grouped specialties according to their demand levels. The analysis identified three stable clusters – “high”, “medium”, and “low” employment prospects – provided actionable recommendations for adjusting curricula and enrollment quotas, and highlighted programs that need additional interdisciplinary digital competencies. The resulting models demonstrated high accuracy (MAE = 13.33%, R² = 0.78) and no multicollinearity issues, as confirmed by VIF values. The proposed methodology offers universities an effective tool for strategic enrollment planning, improving graduate employability, and real-time adaptation of educational offerings to the dynamic needs of the economy. It can also be embedded into digital education-management platforms and regional workforce-demand forecasting systems.