Lead Scratcher: An AI-Powered Smart Job Portal for Automated Resume Evaluation and Intelligent Job Matching

Abstract

The modern recruitment landscape faces significant challenges arising from manual resume screening, lack of ATS (Applicant Tracking System) transparency, and inaccurate job matching methods. This paper presents Lead Scratcher, an AI-powered smart job portal that leverages Artificial Intelligence (AI) and Natural Language Processing (NLP) to automate resume analysis, generate meaningful ATS scores, and deliver personalized job recommendations. The system allows candidates to upload their resumes, which are parsed to extract structured information including skills, work experience, and educational qualifications. A weighted scoring algorithm then computes an ATS compatibility score by evaluating keyword relevance, skill matching, experience alignment, and resume formatting. Additionally, the platform provides actionable improvement suggestions and semantically matched job recommendations for candidates, while offering recruiters ranked profiles and analytical dashboards. Testing results confirm that Lead Scratcher significantly improves recruitment efficiency, reduces manual workload, and enhances the quality of candidate-job alignment compared to conventional systems.

Introduction

This paper introduces Lead Scratcher, an AI-powered smart job portal designed to improve recruitment by addressing the limitations of traditional platforms such as LinkedIn, Naukri.com, Resume Worded, and HireVue. Existing recruitment systems often rely on keyword-based filtering, lack ATS (Applicant Tracking System) transparency, provide limited feedback to candidates, and result in poor job matching and high rejection rates. Lead Scratcher aims to bridge the gap between job seekers and recruiters through the use of Artificial Intelligence (AI), Natural Language Processing (NLP), and semantic analytics.

The system automates resume screening by parsing resumes using NLP techniques to extract skills, experience, education, and other relevant information. It generates an ATS compatibility score based on keyword matching, skill alignment, work experience, and resume formatting. The platform also identifies skill gaps and provides actionable suggestions to help candidates improve their resumes and increase their chances of selection.

Unlike traditional keyword-based recommendation systems, Lead Scratcher uses semantic job matching, which analyzes the contextual meaning of candidate profiles and job descriptions. By utilizing vector-based similarity measures, it provides more accurate and personalized job recommendations. Recruiters benefit from automated candidate ranking, reduced manual screening effort, and improved hiring accuracy.

The system follows a three-tier architecture consisting of an Angular-based frontend, a Spring Boot backend, and a MySQL database. Python NLP libraries such as NLTK and spaCy are used for resume parsing and skill extraction. The platform provides dedicated dashboards for both candidates and recruiters, enabling resume uploads, ATS score viewing, job recommendations, candidate analytics, and recruitment management.

Experimental results show significant improvements over traditional recruitment methods, including approximately 70% reduction in resume screening time, 60% reduction in recruiter workload, improved job-matching accuracy through semantic analysis, real-time candidate feedback, and greater ATS transparency. Most evaluated resumes achieved scores between 61–80%, indicating effective differentiation of candidate-job compatibility.

Comparative analysis demonstrates that Lead Scratcher uniquely combines free ATS analysis, skill gap identification, semantic AI-based job matching, actionable resume feedback, recruiter analytics, and real-time feedback mechanisms within an open-source framework. Overall, the proposed system offers a scalable, cost-effective, and intelligent recruitment solution that enhances hiring efficiency, candidate success, and recruiter productivity.

Conclusion

This paper has presented Lead Scratcher, an AI-powered smart job portal that addresses the critical limitations of traditional recruitment systems through the integration of Natural Language Processing, a weighted ATS scoring algorithm, and semantic job matching. The system successfully automates resume analysis, provides actionable candidate feedback, and delivers personalized job recommendations, while offering recruiters efficient candidate ranking and analytical insights. The experimental results validate that Lead Scratcher achieves significant improvements in recruitment efficiency: approximately 70% reduction in screening time, measurably higher job matching accuracy through semantic analysis, and complete ATS transparency for candidates. All six primary test cases passed successfully, confirming the system\'s functional correctness and reliability. The use of exclusively open-source technologies ensures economic viability for organizations of all sizes.

References

[1] LinkedIn. https://www.linkedin.com. Accessed for understanding job recommendation systems and recruitment workflows. [2] Naukri.com. https://www.naukri.com. Referenced for job portal structure and job listing systems. [3] Spring Boot Documentation. https://spring.io/projects/spring-boot. Used for backend development and REST API implementation. [4] Angular Official Documentation. https://angular.io. Used for frontend development and UI design. [5] MySQL Documentation. https://www.mysql.com. Used for database design and data management. [6] Natural Language Toolkit (NLTK). https://www.nltk.org. Used for resume parsing and text analysis. [7] Jurafsky, D., & Martin, J. H. Speech and Language Processing. Pearson Education. [8] Devlin, J., Chang, M.W., Lee, K., & Toutanova, K. (2019). BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding. NAACL-HLT 2019. [9] Bharadwaj, A., Bhatt, S., & Patel, R. (2021). Resume Screening using Natural Language Processing and Machine Learning. International Journal of Computer Applications, 174(12). [10] Johnson, D.W., & Johnson, R.T. (2014). Cooperative Learning in University Instruction. Journal on Excellence in College Teaching.

Copyright

Copyright © 2026 Himanshu Chouhan, Krishna Jaiswal, Dr. Vandana Kate, Prof. Chanchal Bansal. 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.