Resume Analyzer

Project Title

Resume Analyzer

Project Area of Specialization Computer ScienceProject Summary

In today's world, many people apply for jobs on a daily basis. Often, there are hundreds if not thousands of applications for a single job offering. The process of analyzing and scrutinizing resumes of such a large number of candidates can be a hectic and cumbersome task. Most of the companies receive resumes on a daily basis and this cycle repeats on every job opening. Also it is very difficult for anyone to go through hundreds of resumes documents and if he/she somehow manages to do this task there is highly unlikely that a human analyzer can detect important features of these documents, even if an organization manages to go through properly these documents there are always chances of human error. Along these errors, it is a very hectic and time consuming task to gather resumes and read them one by one. There is potential for an application that can do this task of important information extraction from these documents efficiently. A web app which will receive resumes for a job and extract the desired entities from these documents and hence saving the human effort and time. This web app will perform the above mentioned task itself and generate the useful entities.

Project Objectives

The model will recognize the entities in resumes. Most of the time there is text in the resumes which is not required or not useful. Our model will provide only useful information to the user or analyzer after extracting the entities.

Project Implementation Method

This task will be achieved by sub-domain of Natural Language Processing, known as Named Entity Recognition(NER). We will use NER to develop an application to which a user can upload resume documents in PDF or word format, our deployed model will extract entities and provide them as output

Benefits of the Project

Our app will help organizations to automate the procedure and only extract the useful information or more specifically it will extract useful entities and give it to the user or the analyzer. Therefore, our model will save time and will extract important information efficiently and this task will be performed by using Natural Language Processing techniques.

Technical Details of Final Deliverable

Module1. Website Front-End

Module 2. Named-Entity Recognition module

We will use Natural Language Processing techniques to train a deep learning model. This deep learning model will take the resume (in pdf or word format) as input and extract the required entities from it. The user can then view the extracted entities saving his time and effort.

Tools & Technology

Tools:

Visual Studio Code

MS Word

MS PowerPoint

Jupyter Notebook

PyCharm

Technology:

HTML

CSS

Javascript

Bootstrap

SQL

Python

Prodigy

Spacy

Django/Flask

Django REST Framework

Final Deliverable of the Project Software SystemCore Industry ITOther IndustriesCore Technology Artificial Intelligence(AI)Other TechnologiesSustainable Development Goals Decent Work and Economic GrowthRequired Resources

Item Name	Type	No. of Units	Per Unit Cost (in Rs)	Total (in Rs)
			Total in (Rs)	63000
Prodigy	Equipment	1	63000	63000