AI Skill Path for Intelligent Career Development System Using Generative AI and ATS Analytics

Abstract

The world\'s employment situation has been significantly impacted by the rapid advancement of automation and artificial intelligence (AI). Even though digital hiring systems are very popular these days, many students and young professionals just starting out in their careers struggle to find a suitable way to match their skills with industry demands. To solve this dilemma, the current paper has introduced AI Skill Path which is a smart career development system that assists in planning skills based on data. The system scans resumes, assesses their alignment with Applicant Tracking Systems (ATS), and creates customized career maps with the help of the integration of generative artificial intelligence and analyticsbased guidance. The implementation of AI Skill Path is done with the help of Django as a backend service and React.js as a user interface and the Google Gemini API to generate learning recommendations. ATS resume documents are analyzed to determine technical and soft skills, which are further matched to target job descriptions to determine ATS fit and the competency gap. The system generates a unique learning roadmap based on the determined gaps and involves applicable resources, project ideas, and time-specific guidance. This has been experimentally assessed with 100 anonymized resumes in the domain of software development and data science with a tenfold evaluation speed, average job-skill comparable accuracy of 85 and a user satisfaction rate of 92. The paper will address the system architecture, methodology, experimental findings, and possible future improvements and the contribution the AI Skill Path can make to the progress of transparent and adaptive career guidance systems.

Introduction

This study proposes AI Skill Path, an AI-driven career guidance system designed to bridge the gap between academic learning and real industry requirements. It addresses the common problem faced by students and professionals who struggle to align their resumes and skills with job market expectations, despite increasing use of ATS-based recruitment systems.

The system uses NLP, machine learning, and generative AI (Google Gemini API) to analyze resumes, extract skills, compare them with job descriptions, and compute an interpretable ATS score. Based on detected skill gaps, it generates a personalized, step-by-step learning roadmap that includes courses, projects, timelines, and interview preparation guidance.

Unlike traditional or existing tools that mainly offer keyword-based matching or generic recommendations, AI Skill Path integrates resume parsing, skill gap analysis, and actionable upskilling plans into a single platform. It is built using a full-stack architecture with Django (backend), React.js (frontend), and PostgreSQL database, ensuring scalability and usability.

The literature review highlights that while AI is increasingly used in recruitment and career systems, most existing solutions lack transparency, integration, and actionable learning pathways. They often function as isolated tools without explaining skill gaps or guiding improvement.

The proposed system consists of four main layers: data ingestion and parsing, ATS scoring and skill gap detection, AI-based roadmap generation, and user interaction via a dashboard. Users can upload resumes, view ATS scores, identify missing skills, and track progress over time.

Conclusion

The AI Skill Path project was launched with the aim of bridging the always-present gap between the academic learning and industry expectations of students and early career professionals. Using ATS based evaluation and personalised road map generation, together with artificial intelligence on resume analysis, the system offers users a clear picture of their current skill position and actionable advice on how the same can be improved. Instead of focusing on resume screening, AI Skill Path converts resumes and job descriptions into a structured format of skills, unveils gaps, and suggests time-based learning plans that directly contribute to the development of employability. The proposed approach can be judged as being effective in practice as experimental assessment of 100 anonymized resumes, all of software and data-centric roles, reveals. The fact that an ATS is as accurate as possible in the mid-80% range indicates that the human assessment is remarkably consistent and replicated by the system and has the capability of meaning the same thing. The process of parsing and evaluations of resumes takes a matter of seconds, which means that the overall processing time is about ten times slower than reading resumes manually. These features render the platform appropriate when implementing it in academic settings like college placement units, and in large-scale Internet career guidance systems. Although it has the strengths, there are some weaknesses. The quality of resume parsing is also impacted by document formatting; sometimes a very ornate or complicated layout might result in extraction mistakes. Furthermore, the current skill ontology and evaluation dataset is mostly pertinent to technical disciplines, making it less useful when applied in a non-technical field like healthcare or finance. Depending on third-party AI also runs the danger of latency and rate limits during periods of heavy usage. Furthermore, because it is not yet integrated with live job advertisements or any outside learning environment, the platform is unable to capture real-time labor market developments and monitor learner progress automatically. Furthermore, the support is now restricted to English, therefore reducing its usefulness in multilingual contexts. Even with such constraints, AI Skill Path provides some of the most hopeful directions for future refinement. Including live job portals like LinkedIn, Indeed, or Naukri into the system would enable matching skill gaps with contemporary employment market data and fresh job criteria. By expanding the skill taxonomy and training data across other domains, it would improve generalizability and help in identifying cross-domain skill connections. To improve end-to-end career readiness, the generative AI component might also be used to help with interview preparation by generating mock interviews, job-related questions, and user-specific feedback. Another excellent chance in the medium term is more integrated engagement with professional and educational training ecosystems. Educational institutions and skilling programs can integrate AI Skill Path into their curriculum design and placement processes to examine a huge volume of resumes, identify widespread skill gaps, and develop targeted training programs. By identifying patterns like average ATS, administrative dashboards can also enable data-driven decision-making. Connecting to other sources like Coursera, Udemy, or GitHub would let the system automatically track courses and projects done, therefore continuously updating the user profile and recommendation system as they progress. The research is still pertinent for more overall artificial intelligence-based career development directions going forward. Adding the concepts of explainable artificial intelligence might guarantee that the results of the ATS, learning courses, and predictive insights are backed by unambiguous and understandable explanations. Also improving interdisciplinary and new role knowledge are integrated forms of rule-based logic and semantic representations. AI Skill Path offers a realistic alternative for converting the present résumé-based review mechanism into the vibrant career development system changing the business environment.

References

[1] . Shah, A., Pati, R., Pimplikar, A., Puthran, S., & Singh, A. (2024). Review Of Approaches Towards Building AI Based Career Recommender & Guidance Systems. ScienceOpen Preprints. [2] . Kulugh, V. E., Aondover, K. P., & Faki, A. S. (2025). Artificial intelligence-powered personalised career guidance system. Dutse Journal of Pure and Applied Sciences, 11(1c), 92-104. [3] . Bahalkar, P., Peddi, P., & Jain, S. (2024). AI-Driven Career Guidance System: A predictive model for student subject recommendations based on academic performance and aspirations. Frontiers in Health Informatics, 13(3), 8216-8230. [4] . Mehraj, T., & Baba, A. M. (2019). Scrutinising artificial intelligence based career guidance and counselling systems: an appraisal. International journal of interdisciplinary research and innovations, 7(1), 402-411. [5] Monika, D. S., & Balaji, K. (2025). A Review on AI-Based Chatbots for Personalized Career Guidance. International Journal ofAdvanced Research in Computer Science &Technology (IJARCST), 8(5), 12833-12838. [6] Chuang, S., Shahhosseini, M., Javaid, M., & Wang, G. G. (2024). Machine learning and AI technology-induced skill gaps andopportunities for continuous development of middle-skilledemployees. Journal of Work-Applied Management. [7] Westman, S., Kauttonen, J., Klemetti, A., Korhonen, N., Manninen, M., Mononen, A., ... & Paananen, H. (2021). Artificial Intelligencefor Career Guidance--Current Requirements and Prospects for the Future. IAFOR Journal of Education, 9(4), 43-62. [8] Waikar, R., Tamhane, S., Tale, T., Talekar, R., Tangde, A., Singla, T., & Kalokhe, T. (2024, December). Student career guidance using generative AI. In 2024 International Conference on Artificial Intelligence and Quantum Computation-Based Sensor Application (ICAIQSA) (pp. 1-6). IEEE. [9] Parasa, M. (2023). Bridging skill gaps with SAP’s Talent Intelligence Hub: Real-time analysis and AI-powered learning recommendations. European Journal of Advances in Engineering and Technology, 10(12), 112-115. [10] Sengupta, S., Parab, S., Shetty, S., Nile, V., & Sambhaji, A. (2025, August). Real-Time AI-Based Skill Gap Analysis and Adaptive Career Guidance Using a Generative AI Framework for the Modern Job Market. In 2025 5th Asian Conference on Innovation in Technology (ASIANCON) (pp. 1-6). IEEE. [11] . Majumdar, P. (2025). Empowering skill development through generative AI bridging gaps for a sustainable future. The Scientific Temper, 16, 104-120. [12] . Kushwaha, D. K., Arora, L., Anand, A., Sheth, D., & Khare, S. (2024, December). AI Powered Job Recommendation System. In 2024 [13] . Al-Surmi, A., Bashiri, M., & Koliousis, I. (2022). AI based decision making: combining strategies to improve operational performance. International Journal of Production Research, 60(14), 4464-4486. [14] . Duan, Y., Edwards, J. S., & Dwivedi, Y. K. (2019). Artificial intelligence for decision making in the era of Big Data–evolution, challenges and research agenda. International journal of information management, 48, 63-71. [15] . Steyvers, M., & Kumar, A. (2024). Three challenges for AI-assisted decision-making. Perspectives on Psychological Science, 19(5), 722734. [16] . Phillips-Wren, G. (2012). AI tools in decision making support systems: a review. International Journal on Artificial Intelligence Tools, 21(02), 1240005. [17] . Udeh, C. G. (2025). The role of generative AI in personalized learning for higher education. World Journal of Advanced Engineering Technology and Sciences, 14(2), 205-207. [18] . Binhammad, M. H. Y., Othman, A., Abuljadayel, L., Al Mheiri, H., Alkaabi, M., & Almarri, M. (2024). Investigating how generative AI can create personalized learning materials tailored to individual student needs. Creative Education, 15(7), 1499-1523. [19] . Guettala, M., Bourekkache, S., Kazar, O., & Harous, S. (2024). Generative artificial intelligence in education: Advancing adaptive and personalized learning. Acta Informatica Pragensia, 13(3), 460489. [20] . Bayly-Castaneda, K., Ramirez-Montoya, M. S., & MoritaAlexander, A. (2024, August). Crafting personalized learning paths with AI for lifelong learning: a systematic literature review. In Frontiers in Education (Vol. 9, p. 1424386). Frontiers. [21] . Deng, W., Wang, L., & Deng, X. (2024). Strategies for Optimizing Personalized Learning Pathways with Artificial Intelligence Assistance. International Journal of Advanced Computer Science & Applications, 15(6). [22] . Schlippe, T., & Bothmer, K. (2023). Skill scanner: an AI-based recommendation system for employers, job seekers and educational institutions. International Journal of Advanced Corporate Learning, 16(1), 55. [23] Daryani, C., Chhabra, G. S., Patel, H., Chhabra, I. K., & Patel, R. (2020). An automated resume screening system using natural language processing and similarity. Ethics and Information Technology [Internet]. Volkson Press, 99-103. [24] Gan, C., Zhang, Q., & Mori, T. (2024). Application of LLM agents in recruitment: a novel framework for automated resume screening. Journal of Information Processing, 32, 881-893. [25] Paranthaman, P., Celia, B. R., Vijayalakshmi, V., & Kumaran, V. S. (2024). Resume Screening Automation: Enhancing Recruitment Efficiency with Machine Learning Algorithms. Frontiers in Health Informatics, 13(4)

Copyright

Copyright © 2026 Raj Verma , Yash Tripathi , Priyanshu Singh Chauhan , Sunil Saha . 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.