Job Recommendation a Hybrid Approach Using Text Processing

Abstract

This work is an attempt to collate the data and discover the foremost relevant candidate-job association mapping concurring with the skills, interests, and preferences of a user and to provide a possible job opportunity as an efficient solution. Several personalized content-based and case-based approaches are considered in this regard. The investigation involves several feature-based item representation methods along with feature-weighted schemes. A comparative evaluation of the distinctive perspective is performed utilizing Kaggle data respiratory. The investigation of this study has shown that job transitions can be successfully predicted. The delicacy of the model can be evaluated based on various algorithms of machine learning such as Naïve Bayes, Logistic regression, support vector machine, random forest, K-nearest neighbors, and multilayer perceptron. In this work, the hybrid recommender framework is created to analyze the further investigation in advance to make an identification of the region of opportunity for the prediction of a suitable job. To get the most expected outcome optimization techniques has applied and after utilization of various machine learning algorithms on hybrid approaches, the classifier of Random Forest gives better results. By this examination, the system of job recommendation can give proper assistance to job searchers improving accuracy and scalability.