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
Machine learning based Resume Shortlisting and Classification Einesh Naik1, Dr. Nilesh B. Fal Dessai2 1Student, Department of Information Technology and Engineering, Goa College of Engineering, Farmagudi, Goa,
India
2Head of Department, Department of Information Technology and Engineering, Goa College of Engineering,
Farmagudi, Goa, India ---------------------------------------------------------------------***---------------------------------------------------------------------
Abstract - The recruitment of candidates tailored to specific
streamline their recruitment efforts, identify top candidates more efficiently, and ultimately improve hiring outcomes.
job profiles is a pivotal task for many companies. With the increasing prevalence of online recruitment, traditional hiring methods are proving to be less efficient. These conventional techniques typically involve a labor-intensive process of manually sifting through submitted applications, reviewing resumes, and creating a shortlist of potential candidates for interviews. In the current technological era, job searching has evolved to be more intelligent and accessible. Companies receive a vast number of resumes/CVs, which are not always well-organized. While significant progress has been made in optimizing the job search process, the selection of candidates based on their resume remains a largely manual task. This research presents a survey of methods that could be used for resume shortlisting and classification according to the company’s job description.
The traditional approach to resume screening involves manual review by human recruiters, a process that is not only time consuming but also susceptible to bias. Human biases, whether conscious or unconscious, can influence decisions and inadvertently exclude qualified candidates based on factors such as gender, ethnicity, or educational background. Machine learning presents a transformative solution to these challenges. By training algorithms on historical data of successful hires, organizations can develop models that learn to identify patterns and characteristics indicative of a good fit for a given role. These models can then be deployed to automate the initial screening process, reducing the burden on human recruiters and mitigating bias.
Key Words:
Candidate Classifying, Candidate Shortlisting, KNN, Machine Learning, Cosine Similarity; Random Forest; SVM
1.1 Objectives Shortlisting and Ranking of Resume: Evaluate and rank resumes based on their relevance to the job description provided by the company.
1.INTRODUCTION The conventional job trend, wherein individuals typically settled for one or two positions throughout their entire professional journey, was once prevalent. Employers took pride in having employees committed to their organization for extended periods, often spanning two or three decades.
Segmentation of Resumes: Categorizing resume into different segments or classes based on their suitability for the given job profile. Clustering algorithms or classification models are implemented to achieve this segmentation, helping recruiters quickly identify potential candidates.
However, in the contemporary era, marked by swift technological changes, such scenarios are no longer applicable for most employees and employers alike.
Filtering of Resumes: Filtering of Resumes according to location and percentage or any other criteria.
In the digital age, where job opportunities abound and applicants are plentiful, the process of resume shortlisting and classification poses a significant challenge for organizations. Manual screening of resumes is not only labor-intensive but also prone to human biases and inconsistencies. However, with the advent of machine learning (ML) techniques, there's a newfound opportunity to revolutionize this aspect of talent acquisition.
2. Related Work 2Q-Learning scheme for Resume [1], In this research 2Qlearning framework is proposed. 2Q-learning framework selects the resumes based on the given set of skills specified in the job description. The 2Q-Learning approach involves the selection or rejection of resumes by comparing the resume with the skills or requirements mentioned in the job description by recruiter. In this research NLP model is used for extracting the features from resume. Then extracted skillset from the resume is given to the 2Q-learning agent that matches the skillset and job description and takes the action. The dataset required for training was obtained from
Machine learning offers the promise of automating and optimizing the initial stages of the recruitment process by leveraging algorithms and models to analyze resumes and categorize them based on predefined criteria. By harnessing the power of data-driven insights, organizations can
© 2024, IRJET
|
Impact Factor value: 8.226
|
ISO 9001:2008 Certified Journal
|
Page 2413