Authors : Shaikh Saniya Jameel; Padma Manoj Sharma; Katkure Dhanshree Yuvraj

Volume/Issue : Volume 10 - 2025, Issue 12 - December

---

Google Scholar : https://tinyurl.com/yxexry49

Scribd : https://tinyurl.com/4rfwmswv

DOI : https://doi.org/10.38124/ijisrt/25dec380

Note : A published paper may take 4-5 working days from the publication date to appear in PlumX Metrics, Semantic Scholar, and ResearchGate.

Note : Google Scholar may take 30 to 40 days to display the article.

---

Abstract : This project focuses on the development of an AI-Powered Resume Screening System designed to overhaul traditional, inefficient talent acquisition processes. The system leverages a multi-model AI architecture combining Rule- Based logic, advanced Deep Learning (LSTM and fine-tuned DistilBERT) models, and the Gemini Pro Large Language Model (LLM) to provide objective, data- driven matching scores between candidate resumes and specific job descriptions. Key functionalities include: high-speed screening, real time analytics for HR teams (e.g., market trends, skill gaps), and personalized, constructive feedback generated by the LLM for applicants.

References :

1. Vaswani, A., et al. (2017). Attention Is All You Need. Advances in Neural Information Processing Systems (NIPS), 30. (Source for the foundational Transformer architecture.)
2. Sanh, V., et al. (2019). DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter. arXiv preprint arXiv:1910.01108. (Source for the specific deep learning model used.)
3. Google. (2024). Gemini API Documentation: Generative AI. Retrieved from https://ai.google.dev/docs
4. Streamlit. (2024). Streamlit Documentation. Retrieved from https://docs.streamlit.io