A Model-Based System for Future Job Opportunities Suggestion Using Convolutional Neural Networks (CNNs)

Authors

Mangal Sawle, Vikas kalme

Abstract

Work recommendation systems are important tools that help match job seekers with suitable and relevant work prospects. In this research study, we provide a novel approach to job suggestion based on a Convolutional Neural Network (CNN) model. The technology leverages deep learning algorithms to extract meaningful data from job descriptions and user profiles. This makes it possible for the algorithm to provide precise and customised work recommendations. Since the CNN model is trained on a large-scale dataset that combines user preferences and job adverts, it may potentially learn complex patterns and correlations between job attributes and user preferences. Our trials' results demonstrate that, in terms of suggestion accuracy and relevancy, our approach outperforms traditional techniques. Furthermore, the CNN model provides interpretability by emphasising the fundamental traits and attributes that give rise to each recommendation. It is evident that the recommended strategy has a great deal of potential to improve users' job search experiences and help recruiters find candidates who are a good match for the role. In the future, other data sources will be added, the CNN model will be further improved, and the system's efficacy will be evaluated across a range of user profiles and domains.

Keywords

Convolutional Neural Network, job recommendation, Random Forest, Linear Regression, Logistic Regression, Decision Tree, Naive Bayes, AdaBoost, and Gradient Boosting.

A Model-Based System for Future Job Opportunities Suggestion Using Convolutional Neural Networks (CNNs). Mangal Sawle, Vikas kalme. 2024. IJIRCT, Volume 10, Issue 2. Pages 1-8. https://www.ijirct.org/viewPaper.php?paperId=2404025