Job-candidate classifying and ranking system with machine learning method

Abstract

Finding suitable candidates for an open job position could be a repetitive and time-consuming task, especially from a large pool of candidates. Besides, this task could truly make fair screening and shortlisting tedious. Losing the opportunity to hire top talent candidates due to the slow screening process or the wrong selection by human error is unacceptable. This paper presented a method for human resources to categorize and select the top candidates for job opening they applied for. The proposed system directed to alter a machine learning algorithm to classify the candidate into groups i) shortlist and ii) not-suitable. The productive preprocessing data approaches of many works were applied. The Decision Tree, Support Vector Machine, Gaussian Naive Bayes, Random Forest, k-Nearest Neighbour, CatBoost, Extreme Gradient Boosting, and Convolution Neural Network were compared to find the most suitable classification model. Then, the system ranked the candidates in a shortlist group in descending order. The proposed system operates an accuracy of 83.5%, weighted f1-score of 86%, and recall of 79% from the Support Vector Machine classifier. This enables the business to identify suitable candidates for a certain position and make more informed decisions about who to invite for an interview.