Volume 15, Issue 7 · IJARST · ISSN 2319-1783 / 2320-1126

AI-Based Resume Driven Interview System with Performance Analytics: Design and Evaluation of a Cost-Optimized Mock Interview Platform with Multi-Provider AI Fallback

AI-Based Resume Driven Interview System with Performance Analytics: Design and Evaluation of a Cost-Optimized Mock Interview Platform with Multi-Provider AI Fallback is an open-access, peer-reviewed research paper by Mamidi Manikanta1, Mrs. Mehaboob Karishma2, published in Volume 15, Issue 7 of the International Journal of Advanced Research in Science and Technology (IJARST), a UGC-approved journal (Print ISSN 2319-1783, Online ISSN 2320-1126).

Author

Mamidi Manikanta1, Mrs. Mehaboob Karishma2

Abstract

This paper introduces the proposed AI-Based Resume Driven Interview System, a resilient, full-stack, and self-hosted platform designed to bridge the gap between academic interview preparation and professional employment through personalized simulation. Standard mock-interview solutions frequently rely on static question banks that fail to match a candidate's background, or depend heavily on single-provider cloud APIs that are susceptible to latency spikes, rate-limiting, and cost barriers. The System leverages natural language processing to extract skills and achievements from candidate resumes to generate tailored questions. To address the vulnerability of proprietary model failures, we design a thread-safe multi-provider fallback engine spanning Google Gemini, Groq, OpenRouter, Hugging Face, and a local deterministic fallback path. The backend additionally applies concrete memory-optimization techniques (lazy model loading, bounded worker/thread configuration) intended for low-RAM hosting environments. A simulation-based evaluation modeling typical provider latency and reliability characteristics indicates the architecture is projected to maintain sub-second average response times and near-complete failover coverage under concurrent load, pending live validation, suggesting the design is suitable for cost-constrained automated career coaching deployments.

DOI: https://doi.org/10.62226/ijarst20262751

References

[1] S. Kulkarni, et al., "Information Extraction from Resumes Using Rule-Based and Machine Learning Techniques," Journal of Talent Acquisition, vol. 12, no. 3, pp. 145-156, 2019.

[2] S. Yu, et al., "Resume Information Extraction Using Conditional Random Fields," IEEE Transactions on Knowledge and Data Engineering, vol. 32, no. 6, pp. 1102-1115, 2020.

[3] J. Devlin, et al., "BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding," Proceedings of NAACL-HLT, pp. 4171-4186, 2019.

[4] A. Singh and P. Gupta, "Domain-Specific Resume Parser Using Fine-Tuned Transformer Networks," ACM Transactions on Intelligent Systems and Technology, vol. 13, no. 4, pp. 55-72, 2022.

[5] S. Valenti, et al., "An Overview of Current Research on Automated Essay Grading," Journal of Information Technology Education, vol. 2, no. 1, pp. 319-330, 2003.

[6] Y. Liu, et al., "Evaluating Large Language Models on Short Answer Grading Tasks," International Journal of Artificial Intelligence in Education, vol. 33, no. 2, pp. 241-260, 2023.

[7] T. Brown, et al., "Language Models are Few-Shot Learners," Advances in Neural Information Processing Systems, vol. 33, pp. 1877-1901, 2020.

[8] T. Baur, et al., "Novice-Agent Interaction in a Virtual Interview Training System," Proceedings of the 13th International Conference on Intelligent Virtual Agents, pp. 232-245, 2013.

[9] K. Anderson, et al., "TARDIS: A Virtual Agent Framework for Helping Young Adults Prepare for Job Interviews," ACM Transactions on Interactive Intelligent Systems, vol. 4, no. 2, pp. 12-32, 2014.

[10] D. Mellet-d'Huart, et al., "MySCoT: My Smart Coach for Training in Job Interviews," Computers & Education, vol. 108, pp. 92-105, 2017.

[11] R. Zhao, et al., "Generative AI Agents in Education: A Survey of Conversational Mentors," IEEE Access, vol. 12, pp. 10245-10260, 2024.

[12] H. Chen and M. Lee, "Designing Persona-Based Large Language Model Recruiter Systems for Dynamic Human Interaction," Computers in Human Behavior, vol. 162, pp. 108-121, 2025.

[13] M. Raghavan, et al., "Mitigating Bias in Algorithmic Hiring Evaluators," Proceedings of the 2020 Conference on Fairness, Accountability, and Transparency, pp. 469-481, 2020.

[14] A. Vaswani, et al., "Attention is all you need," Advances in Neural Information Processing Systems, pp. 5998-6008, 2017.

[15] A. Radford, et al., "Language models are unsupervised multitask learners," OpenAI Blog, vol. 1, no. 8, p. 9, 2019.

DOI

https://doi.org/10.62226/ijarst20262751

PAGES : 2314-2318 | 4 VIEWS | 2 DOWNLOADS

How do you cite this paper?

Mamidi Manikanta1, Mrs. Mehaboob Karishma2 — “AI-Based Resume Driven Interview System with Performance Analytics: Design and Evaluation of a Cost-Optimized Mock Interview Platform with Multi-Provider AI Fallback.” International Journal of Advanced Research in Science and Technology (IJARST), Volume 15, Issue 7. DOI: https://doi.org/10.62226/ijarst20262751.

Download Full Article