Applying Machine Learning Techniques to Automatically Process and Match Candidates Applications to Job Descriptions

点击翻译按钮获取中文摘要

TAS (Techno Aero Services inc.) is a Canadian recruitment agency specialized in aeronautics, engineering, andtechnology. At TAS, candidates currently submit resumes to a database through a web interface. These resumesare then manually processed by recruiters before a suitable candidate is matched to a position. Through thislaborious manual process, great prospective candidates often get lost in the piles. This project aims to leveragetext mining and machine learning techniques to automatically collect information about prospective candidatesfrom their submitted resume and public profiles on websites like Linked In, Twitter, and Facebook to providerecruiters with an overall picture of a candidate's strengths and weaknesses. Both the technical andcommunication skills of the candidates will be analyzed and summarized. The goal is to provide recruiters withthe information they need to judge a candidate on both his mastery of key skills and his ability to fit into thecompany culture.To achieve this goal, we will leverage big data processing infrastructure, including machine learning throughframeworks like Google Tensorflow, to automatically extract useful information from textual data aboutprospective candidates. Deep learning approaches have proved to be powerful tools for patterns recognition andclassification in diverse problems, such as speech, text, and image recognition. We expect it to also achieve agood performance in automatically detecting useful signal about prospective candidates from data collectedabout them from their resume and the Web.