Intelligent System for Resume Evaluation and Campus Placement Selection

Abstract

Shortlisting students during campus placements is a time-consuming task for Training and Placement Officers, especially when many resumes need to be reviewed. Manual screening may lead to delays and inconsistencies. To reduce this effort, a web-based resume screening system is developed. The system allows resumes in PDF or Word format to be uploaded and lets officers set basic requirements such as skills and academic marks. It reads the resume content and matches it with the given criteria using simple keyword checking. Based on this, the system gives a basic score and selects suitable candidates. The final shortlisted list is saved in an Excel file, and email notifications are sent to students. This system helps in organizing the placement process and reduces manual workload.

Introduction

Campus placements have become increasingly competitive due to a large number of students applying for limited job opportunities. The traditional manual process used by Training and Placement Officers (TPOs) to screen resumes is time-consuming, error-prone, and often fails to properly evaluate technical skills and project experience. It also struggles to efficiently match students with diverse job roles such as web development, data science, and cloud computing.

To address these issues, the proposed system introduces an automated resume screening and shortlisting system that uses Artificial Intelligence (AI) and Natural Language Processing (NLP) techniques. The system allows resumes (PDF/Word) to be uploaded, extracts and analyzes content, and matches it with predefined job requirements using keyword-based skill extraction.

System Objectives

The system aims to:

• Automate resume screening and shortlisting
• Extract skills using NLP techniques
• Evaluate candidates across multiple domains (Frontend, Backend, Cloud, etc.)
• Generate suitability scores based on academic and technical parameters
• Produce shortlisted reports in Excel format
• Send automated email notifications to selected students
• Improve speed, accuracy, and fairness in placements

Methodology and Workflow

The system works in a structured pipeline:

1. Resume Upload (PDF/Word format)
2. Text Extraction and Cleaning
3. Keyword-based Skill Extraction (NLP)
4. Domain Classification (Frontend, Backend, ML, etc.)
5. Score Calculation based on skills and academics
6. Shortlisting based on threshold score
7. Report generation (Excel) and email notification

System Design and Implementation

• Frontend: Built using HTML, CSS, JavaScript, and React for user interaction and resume upload.
• Backend: Developed in Python using Flask for processing resumes, scoring, and managing APIs.
• Database: Stores student data, resumes, scores, and results.
• Core Modules: Resume parsing, NLP processing, scoring engine, and shortlisting system.

Key Functional Modules

• Student registration and record management
• Resume upload and parsing
• Skill extraction using keyword matching
• Candidate evaluation and scoring
• Company requirement matching
• Automated shortlisting and reporting

Output and Features

• Generates ranked shortlisted candidate list
• Exports results in Excel format
• Sends automated email notifications via SMTP
• Improves efficiency in handling large volumes of resumes

Conclusion

This paper presents a simple resume evaluation and student shortlisting system for campus placements. The system helps in automating the resume screening process and evaluating candidates based on their skills and basic academic criteria. It extracts important information from resumes and shortlists suitable students according to predefined requirements. The system performs better than manual methods by making the process faster and more organized. The web interface allows Training and Placement Officers to upload resumes, set requirements, and view results easily. It also generates an Excel report and sends email notifications to shortlisted students. Overall, the system reduces manual effort and improves the speed and accuracy of the placement process. It provides an efficient way to manage large numbers of student resumes. Future improvements can include more advanced techniques and better integration with external systems to improve performance further.

References

[1] N. Kumar and A.S. Singh present a machine learning-based approach for predicting student placement outcomes using academic and skill-based data (International Journal of Engineering Research,2020) [2] K. Acharya describes a centralized college training and placement system designed to mange student data and recruitment processes efficiently (International Journal of Computer Applications,2024) [3] E. Barnett and P. Bergman propose a data analytics-based approach for evaluating student placement readiness using multiple performance indicators (Educational Evaluation Journal,2018) [4] S. Sharma and R. Meha present an automated resume screening system using Natural Language Processing techniques for extracting skills and relevant information from resumes (International Journal of Computer Applications,2021) [5] P. Gupta and S. Kumar demonstrate the use of machine learning algorithms for student placement prediction based on academic performance and technical skills (International Journal of Engineering and Technology,2019). [6] A. Verma and K. Patel propose an AI-based Recruitment system for automated candidate evaluation and ranking using intelligent algorithm (International Journal of Advanced Computer Science, 2022). [7] M. Singh and R. Kaur describe the use of NLP-based keyword extraction techniques for identifying skills and domain knowledge from unstructured resume data (IEEE Access, 2021). [8] J. Lee and H. Kim present a multi-domain candidate evaluation system that analyzes technical skills across different fields such as software development and data science (IEEE Transaction on Education, 2020). [9] R. Patel and D. Shah develop an email automation system using SMTP protocol for efficient communication in web-based applications (International Journal of Computer Science and Information Security, 2018). [10] S. Rao and V. Reddy propose an Al-based smart recruitment system that integrates resume analysis, candidate scoring, and automated shortlisting (International Journal of Innovation Technology and Exploring Engineering, 2023).

Copyright

Copyright © 2026 Mrs. P. Neelima, V. Monika, Sk. Afrin, T. Nancy, Y. Harshitha. This is an open access article distributed under the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.