International Journal of Science, Engineering and TechnologyAuthors: Raj Guru, Mahak Devi, Rudrakshi Narayan Srivastava, Divyanshu Salwan, Alankrita Agarwal
Abstract: Career selection is a crucial yet often confusing stage for students, especially in technology-related disciplines where numerous options exist. Traditional counseling methods mainly rely on academic performance or general aptitude, overlooking the influence of personality and learning preferences. This paper presents an AI-driven career guidance system that integrates psychometric profiling with machine learning models to gener- ate personalized career recommendations. The system analyzes individual traits using validated psychological frameworks—Big Five Personality Traits, Myers–Briggs Type Indicator (MBTI), and VAK learning styles—together with self-assessed technical skill ratings. A custom dataset was developed through an online survey of undergraduate computer science students, combining psychometric attributes, technical competencies, and preferred career roles. Multiple machine learning algorithms, including Logistic Regression, Support Vector Machine, Random Forest, and Multi-Layer Perceptron, were trained and evaluated using accuracy, precision, recall, and F1-score. The best-performing model achieved an accuracy of [insert your actual result]%, demonstrating that combining psychometric and technical fea- tures significantly improves prediction reliability. The system further incorporates a hybrid recommendation module to suggest relevant courses and estimate salary ranges. Deployed as a web- based application, it provides accessible, explainable, and data- driven career advice for students and educators. The proposed framework establishes a foundation for future enhancements such as adaptive learning and integration of real-time labor market analytics.
DOI: https://doi.org/10.5281/zenodo.17568203
