CareerPath AI: A Hybrid Machine Learning And Large Language Model Framework For Multi-level Career Recommendation With Real-Time Job Market Integration

Read full text Summarise with VIRAT
Authors: Mrs S.T. Ramya, T Sri Vardhini, B Sneha Reddy, M Naga Sai
Cited by: 0
References: 1

Summary

No summary yet. VIRAT can read this paper and write a plain-language summary of its aim, methods, key findings and limitations.

Summarise with VIRAT Free to try with your Science Catalogs account.

Abstract

Career selection is a critical decision that significantly influences a student's academic trajectory and longterm professional success.However, students at the 10th, 12th, and graduate levels often experience uncertainty due to limited awareness, evolving job market demands, and insufficient personalized guidance.Existing career recommendation systems largely focus on specific domains and rely on static datasets, limiting adaptability and holistic assessment.This paper proposes a Hybrid AI-Based Career Recommendation System that integrates Machine Learning models (Decision Tree and XGBoost) with Large Language Models (LLMs) to deliver explainable, adaptive, and personalized career guidance across Arts, Commerce, Science, Humanities, and vocational streams.The system first classifies users based on educational level and evaluates academic performance, interests, aptitude, personality traits, and psychometric responses.Structured prediction models generate career probabilities, while LLMs provide contextual explanations, learning pathways, and actionable recommendations.To ensure industry relevance, real-time job market trends and skill-demand data are incorporated through external APIs.A skill-gap analysis module identifies competency gaps and recommends targeted courses and certifications.A feedbackdriven ranking mechanism further refines predictions and assigns a probability-of-success score to each recommendation.Experimental evaluation demonstrates improved predictive accuracy and personalization compared to conventional career guidance approaches.The proposed framework bridges the gap between education and employability through a scalable, data-driven, and future-ready decision support system.

Fields of Study & Subjects

Recommender Systems and Techniques Edcuational Technology Systems Online Learning and Analytics

Publication details

Journal / source
International journal of engineering science and advanced technology.
Volume
26
Issue
3
Pages
447–452
Publication date
1 March 2026
Language
EN