International Research Journal of Engineering and Technology (IRJET)
e-ISSN: 2395-0056
Volume: 11 Issue: 04 | Apr 2024
p-ISSN: 2395-0072
www.irjet.net
JOB AND SKILLS RECOMMENDATION SYSTEM FOR JOB SEEKERS AND RECRUITERS Bhavani R1, Harikrishna P2, Sabarinathan S3, Yaswanth K4 1234Dept. of Computer Science and Engineering, Government College of Engineering Srirangam, Tamil Nadu, India
---------------------------------------------------------------------***--------------------------------------------------------------------2. RELATED WORKS Abstract - In today's dynamic job market, both job seekers and recruiters face challenges in matching skills to job requirements efficiently. The Job and Skills Recommendation System (JSRS) aims to address this by providing personalized recommendations to job seekers and recruiters based on their respective needs and preferences. For job seekers, JSRS offers a user-friendly interface where they can input their skills, qualifications, and career preferences. Leveraging advanced algorithms and machine learning techniques, JSRS analyzes this information along with historical job data to generate tailored job recommendations. These recommendations consider factors such as job relevance, career growth opportunities, and geographical preferences, enabling job seekers to discover suitable job openings quickly and easily. Ultimately, JSRS aims to bridge the gap between job seekers and recruiters, facilitating mutually beneficial connections that drive success in today's competitive job market.
This section aims to review the existing t techniques for job and skill recommendation. Alsaif et al. [1] developed a bi-directional recommendation system using NLP techniques to match job seekers with job recruiters. The system includes web scraping, data pre-processing, NLP model training, and bi-directional matching steps, utilizing sa.indeed.com data. Named entities detection and validation using precision metrics were conducted, with Word2vec employed for term retrieval to enhance matching efficiency. Mahalakshmi et al. [2] developed a Job Recommendation System focusing on skill sets to aid college graduates in finding fitting employment. It analyzes resumes to suggest tailored job opportunities and recommend skill enhancements. Employing preprocessing techniques and cosine similarity, it offers hierarchical job recommendations, aiming to reduce unemployment and foster career growth. Desai et al. [3] developed an Automated Job Recommendation System using Collaborative Filtering for personalized job suggestions. The system integrates user-based and itembased algorithms, utilizing student resumes and recruitment details for tailored recommendations. It encompasses data preprocessing, collaborative filtering, and evaluation phases, offering a promising solution to traditional job search inefficiencies. Mhamdi et al. [4] developed a Job Recommendation System using Profile Clustering and Job Seeker Behavior analysis, offering personalized suggestions by clustering job attributes and aligning with user behavior. Enhance accuracy by integrating Word2vec and k-means clusterings. Punitavathi et al. [5] proposed a three-tier architecture for an online job and candidate recommendation system, utilizing PHP Standards Recommendation (PSR) and text field filtering for efficient data management. The model integrates recommender system technology and web services to provide personalized recommendations, ensuring privacy through encryption. Their system effectively manages data flow, tackling information overload in online recruiting for robust and personalized recruitment processes.
Key Words: Machine Learning, Natural Language Processing, Job and Skills Recommendation System, K Nearest Neighbor, Term Frequency-Inverse Document Frequency.
1.INTRODUCTION In today's rapidly evolving job market, the process of matching job seekers with suitable employment opportunities and recruiters with qualified candidates has become increasingly complex. With the abundance of job postings and resumes available online, both job seekers and recruiters face the daunting task of sifting through vast amounts of information to find the perfect match. Traditional methods of recruitment often rely on manual sorting and keyword matching, which can be timeconsuming, inefficient, and prone to biases. To address these challenges, advanced technologies such as Artificial Intelligence (AI) and Machine Learning (ML) are being leveraged to develop innovative solutions that streamline the job search and recruitment process. One such solution is the development of JSRS, which aim to revolutionize the way job seekers find employment opportunities and recruiters identify top talent. By utilizing sophisticated algorithms and data analytics techniques, JSRS offers personalized recommendations based on the skills, preferences, and requirements of both job seekers and recruiters.
© 2024, IRJET
|
Impact Factor value: 8.226
|
ISO 9001:2008 Certified Journal
|
Page 1026