In the context of the rapid development of digital educational technologies and the introduction of modular programs in higher education institutions, there is a growing need for intelligent systems capable of performing in-depth analysis of academic data and generating predictive models aimed at improving students' academic performance and career support. This study is designed to develop an intelligent model based on the factor analysis method for predicting the academic performance and career trajectory of students studying in the IT specialty. The model uses grades in the main subjects of modular educational programs as input data. Principal component analysis (PCA) was used to identify a latent factor structure, which is interpreted as two dominant components: "Theoretical preparation" and "Practical preparation". The obtained factor scores are used as features in a logistic regression model, which shows high accuracy in classifying career outcomes (ROC-AUC ≈ 0.95). This allows not only to perform binary predictions (success/failure), but also to quantitatively assess the contribution of educational modules to a student's career trajectory. The results of the study confirm the potential of the proposed model as an educational analysis tool capable of identifying hidden dependencies in academic data, profiling students according to their developmental trajectories, and providing interpretable recommendations to teachers and curriculum coordinators. The proposed approach can be scaled and integrated into learning management systems (LMS), digital career guidance platforms, and student competency support systems.