Offering:
AI Jumpstart

Business Category:
Recruitment Process Outsourcing (RPO)

Project Years:
2024

Problem/Opportunity

The client has a third party resume parser that integrates well with the system. However there is a cost that is incurred for parsing each resume. The client wishes to develop an in-house utility for this resume parser.

Outcome

DC is able to develop an in-house resume parser and this would replace the third party utility. We did a comparative study of several resume parsing tools along with inhouse parsing tool developed. The results were found to be comparable and satisfactory. This has resulted in a significant amount of cost savings for the client.

Execution

We used Python Libraries such as PyPDF2 to extract the text from PDF Documents. The text was pre-processed using the library re for cleaning and spaCy, nltk as well as HuggingFace Transformer models to obtain the various information that requires to be parsed. We finally structure extracted information into dictionary format for easy handling.