International Research Journal of Engineering and Technology (IRJET)
e-ISSN: 2395-0056
Volume: 11 Issue: 10 | Oct 2024
p-ISSN: 2395-0072
www.irjet.net
COURSE RECOMMENDATION SYSTEM BASED ON RESUME ANALYSIS USING CONTENT BASED FILTERING Karpagam.V1, Shree Harinee.T.G2, ,Swastika.R.A3 1Assistant Professor, Computer Science &Engineering, K.L.N. College of Engineering, Sivagangai, TamilNadu, India. 2Student, Computer Science &Engineering, K.L.N. College of Engineering, Sivagangai, Tamil Nadu, India, 3Student, Computer Science &Engineering, K.L.N. College of Engineering Sivagangai, Tamil Nadu, India.
---------------------------------------------------------------------***--------------------------------------------------------------------Abstract - To align candidate skills with industry demands is essential in today’s competitive job market. This work introduces an intelligent course recommendation system designed to analyze resume content and provide personalized learning paths that bridge skill gaps for specific job roles. The system leverages BERT (Bidirectional Encoder Representations from Transformers) to accurately extract and contextualize key skills, experiences, and qualifications from resumes. By applying Cosine Similarity measures, identifies discrepancies between a candidate’s current competencies and job requirements, highlighting areas for improvement. To enhance recommendation accuracy, the system integrates the Random Forest algorithm, classifying and prioritizing courses based on their relevance to addressing identified skill gaps. This hybrid approach ensures that recommendations are tailored to individual profiles while remaining aligned with evolving industry needs. Additionally, the system adapts to user inputs, allowing for continuous updates as candidates refine their resumes or acquire new skills, delivering realtime, highly relevant course suggestions. The outcome is a personalized and strategic learning pathway that significantly boosts employability by guiding candidates toward courses that directly support their career goals. This innovative solution provides educational institutions, training platforms, and career services with a powerful tool for enhancing career development through highly targeted and effective learning experiences.
requirements of the target job, highlighting areas for development. To enhance recommendation accuracy, the system integrates the Random Forest algorithm, which classifies and prioritizes courses based on their relevance to the identified skill gaps. This hybrid approach ensures that recommendations are tailored to individual profiles while staying aligned with evolving industry needs. By adapting to user inputs, the system continuously updates, offering real-time, highly relevant course suggestions as candidates refine their skills. This personalized learning pathway significantly boosts employability, providing a strategic solution for educational institutions, training platforms, and career services to deliver targeted, effective learning experiences.
2. RESEARCH AND FINDINGS In today’s rapidly evolving job market, aligning candidate skills with industry demands is more critical than ever. Traditional methods for skill development often fail to address specific gaps between a candidate’s current qualifications and the competencies required by employers. These methods can be inefficient, subjective, and unable to adapt quickly to individual needs. As the demand for more precise, data-driven approaches to career development grows, there is a need for intelligent systems that can offer personalized and dynamic solutions to enhance employability. Machine learning, particularly the use of advanced models like BERT (Bidirectional Encoder Representations from Transformers), offers promising solution to these challenges. By analyzing large amounts of resume data, BERT Course Recommendation System based on Resume Analysis using Content-based filtering can accurately extract and contextualize the skills, experiences, and qualifications of candidates. This system compares those extracted features against job requirements using Cosine Similarity, identifying skill gaps that need to be addressed for a candidate to be better aligned with their desired role. This research aims to explore how BERT and Random Forest algorithms can work together to create a personalized course recommendation system that addresses these skill gaps efficiently.
Key Words: Content Based Filtering, BERT, Cosine Similarity, Random Forest, Personalized Learning.
1.INTRODUCTION As today’s job market becomes increasingly competitive, aligning candidates skills with industry demands is critical for career success. An intelligent course recommendation system is introduced to analyze resumes and offer personalized learning paths to bridge skill gaps for specific job roles. Utilizing BERT (Bidirectional Encoder Representations from Transformers), the system extracts and contextualizes key skills, experiences, and qualifications from resumes. By applying Cosine Similarity, it identifies discrepancies between a candidate’s current competencies and the
© 2024, IRJET
|
Impact Factor value: 8.315
|
ISO 9001:2008 Certified Journal
|
Page 605