Data-Driven Resume Analysis Using Natural Language Processing and an Ensemble of Deep Learning

Effective recruitment and selection practices are critical factors to the entry point of human resources in any organization. They also tend to determine an organization’s success and sustainability. Well-conducted recruitment and selection process is essential for any organization, permitting in-depth and objective verification of candidates to meet employers’ expectations and lead to their employment. With the increasing number of job seekers, employers need to take appropriate measures to quickly obtain the key information of job seekers and make their selections effectively. The massive volume of applications that organizations receive can no longer be handled with manual processes. Moreover, recruitment process implemented using manual, biased, and subjective evaluation will always result in a lower job and organizational fit, leading to decrease in overall talent quality. The current job recruitment horizon demands better approaches for efficient resume-parsing technologies and methods. Even though there are several elementary techniques for parsing structured documents, they are not suitable for processing unstructured documents like resumes. AI-enabled recruiting systems have evolved to resolve these hitches in recruitment. In this study, we propose a neural network ensemble approach using Bi-directional Long Short-Term Memory (Bi-LSTM), Convolutional Neural Network (CNN), and Conditional Random Field (CRF), as the base learners.