Resume Ranker: AI-Based Skill Analysis and Skill Matching System
In response to Japan's imminent labor shortage crisis and its sluggish integration of IT into industry, an innovative AI-Based Skill Analysis and Matching System is proposed. With projections indicating a demand for 7 million foreign workers by 2040, there arises an urgent need for streamlined HR training processes. The system leverages advanced technologies to accelerate candidate selection and job matching, encompassing resume parsing, keyword filtering, skill matching, and improvement. Methodologically, various libraries, modules, and NLP models are integrated for comprehensive data extraction and analysis. Techniques such as tokenization, lemmatization, and cosine similarity-based matching optimize the alignment of candidates with job requirements. Findings demonstrate the system's effectiveness in reducing recruitment time and effort, enabling recruiters to focus on assessing relevant candidates efficiently. Additionally, the system offers tailored skill enhancement recommendations to candidates, facilitating their integration into the Japanese workforce. The significance of this research lies in its contribution to mitigating Japan's labor shortage crisis and advancing HR management practices. By harnessing AI technologies, the system not only addresses immediate labor market needs but also sets the stage for a technology-driven approach to talent acquisition. Overall, this research fosters advancements in HR management, benefiting employers and job seekers within and beyond Japan.
Authors
- Samantha Thelijjagoda (ORCID: https://orcid.org/0000-0002-0548-1603)
- Nishantha Giguruwa
- Nikethani Gangoda
- Kavindu Piumal Yasantha
- Chamina Sewwandi
- Navindu Induvara
Institutions
- Ritsumeikan Asia Pacific University (JP)
- Sri Lanka Institute of Information Technology (LK)
Publication Details
- Published
- 2024-10-23
- DOI
- https://doi.org/10.1109/icds62089.2024.10756304
- Citations
- 7
- Primary Topic
- Higher Education Learning Practices
- Type
- article
- Field-Weighted Citation Impact
- 14.67