Designing a precision career-guidance model based on student psychological profiling in higher education

Area of Science:

• Educational Technology
• Artificial Intelligence in Education
• Career Counseling

Background:

• Higher education requires personalized, data-driven career guidance.
• Traditional methods lack personalization for diverse student needs and aspirations.

Purpose of the Study:

• To propose the Psychological Profiling Driven Career Guidance Model (PPDCGM) for precision career guidance.
• To develop an Adaptive Career Pathway Strategy (ACPS) for dynamic recommendation refinement.

Main Methods:

• Integrating psychological profiling with machine learning for personalized recommendations.
• Implementing the framework on public career trajectory benchmarks.
• Assessing precision via next career prediction.

Main Results:

• The PPDCGM framework demonstrated consistent improvements over baselines.
• Achieved superior MRR and Recall@10 on KARRIEREWEGE and DECORTE datasets compared to MiniLM.
• Results indicate effectiveness and robustness in intelligent educational recommendations.

Conclusions:

• The proposed PPDCGM framework offers a practical and effective solution for intelligent career guidance.
• The Adaptive Career Pathway Strategy enhances recommendation relevance.
• The study validates the framework's value for higher education.