Screening and Ranking Resumes using Stacked Model
Rasika Ransing, Akshaya Mohan, Nikita Bhrugumaharshi Emberi, Kailas Mahavarkar
Abstract
Talent acquisition is essential for all companies irrespective of the size of their business. As it is next to impossible to look through numerous resumes manually, we have created an automated resume screening application. This system makes use of Machine Learning algorithms such as KNN, Linear SVC, and XGBoost. A two-level stacked model containing all these algorithms is constructed which helps in predicting specific job profiles from a text description accurately. This framework can be valuable for organizations to waitlist competitors and furthermore for the applicants who can check if their resume is very much shaped for the system to recognize right work profiles from it. A ranking system is also implemented, for the companies, featuring the most relevant profiles on the top.