A New Feature Extraction Approach to Extract Area of Expertise from Resumes to Augment the Hiring Process

Abstract

Text Feature extraction is a process of detecting and discovering promising data from a large unordered textual data set. The main objective of the feature extraction process is to unearth the promising data and transmit them in to acceptable format to help in decision making. With the ever evolving digital technology number of resumes posted everyday seeking for a job increases steeply and this voluminous data intricate the recruitment firms to identify the right candidate for the right job. The main objective of this paper is to deals with a new feature extraction approach using ranking based frequent text occurrences to extract promising texts from the resume dataset and reduces the hiring agencies manual work considerably, reduces the dimensionality of the data to a larger extent and thereby reduces the running or execution time and memory footprints required largely when compared with the existing approaches.