Volume: 2 Issue: 2
Year: 2025, Page: 48-53, Doi: https://doi.org/10.70968/ijeaca.v2i2.ML101
Received: July 26, 2025 Accepted: Nov. 25, 2025 Published: Dec. 12, 2025
Getting into the Indian Armed Forces asks far more of a candidate than strong exam scores. Competitive screenings such as NDA, CDS, AFCAT, and CAPF test aspirants across Mathematics, English, General Knowledge, and Logical Reasoning at considerable depth, while the Service Selection Board (SSB) scrutinises personality, leadership capacity, and psychological fitness. Most students prepare through offline coaching and generic online test series that offer no real personalisation, no deep analytics, and no connection between written exam practice and SSB readiness. YodhaAI was built to close those gaps. The platform gives aspirants full-length mock tests, subject-specific drills, and short practice quizzes. Every session generates data that the system uses to surface accuracy trends, recurring weak spots, and progress trajectories. Built on the MERN stack (MongoDB, Express.js, React.js, Node.js) with JWT-based authentication, YodhaAI presents performance insights through interactive dashboards. The planned roadmap adds NLP-driven question generation using transformer models, performance forecasting, and adaptive study recommendations — progressively turning the platform into a virtual preparation mentor that evolves alongside each student.
Keywords: YodhaAI: An Intelligent Hub for Defence Aspirants
1. Woolf B. <I>Building Intelligent Interactive Tutors</I>. Morgan Kaufmann. 2010; Available from: https://doi.org/10.1016/b978-0-12-373594-2.00008-3
2. Anderson J, <I>et al</I>. Cognitive modeling and learning analytics. <I>Journal of Learning Sciences</I>, 27(3), pp. 301-335, 2018.
3. Zhang L, <I>et al</I>. Reinforcement learning for adaptive assessment. <I>IEEE Transactions on Learning Technologies</I>, 13(2), pp. 210-221, 2020.
4. Patel A, Deshmukh R. MERN stack implementation in scalable educational platforms. <I>International Journal of Computer Applications</I>, 183(21) pp. 10-15, 2022.
5. Li H, <I>et al</I>. Data visualisation in learning analytics. <I>Computers & Education</I>, 165, Art. no. 104143, 2021.
6. Devlin J, Chang M, Lee K, Toutanova K. BERT: Pre-training of deep bidirectional transformers for language understanding. Proceedings of the 2019 Conference of the North. 2019; Available from: https://doi.org/10.18653/v1/n19-1423
7. Sahu P, Gupta N. AI-generated MCQs using fine-tuned BERT models. <I>Journal of AI Research and Development</I>,12(3), pp. 45–52, 2023.
8. Kumar R, Mehta S. NLP-driven evaluation techniques for SSB assessments. <I>Journal of Defence Technology</I>, 18(4), pp. 88-95, 2022.
9. Mehta S, Shah P. AI-powered personalised learning for defence exam preparation. <I>International Journal of Educational Technology</I>, 10(2), pp. 33–40, 2023.
10. Mikolov T, Chen K, Corrado G, Dean J. Efficient estimation of word representations in vector space. <I>Proc. ICLR Workshops</I>, 2013.
11. Getting Started with Scikit‐learn for Machine Learning. Python® Machine Learning. 2019; Available from: https://doi.org/10.1002/9781119557500.ch5
12. Vaswani A, <I>et al</I>. Attention is all you need. <I>Advances in Neural Information Processing Systems</I> (NeurIPS), 2017.
13. MongoDB Inc.. <I>MongoDB Documentation</I>. [Online].. Available from: https://www.mongodb.com/docs/
14. Meta Platforms Inc.. <I>React — A JavaScript library for building user interfaces</I>. [Online]. Available from: https://reactjs.org/
15. Recharts Team. <I>Recharts Documentation</I>. [Online]. Available from: https://recharts.org/
© 2025 Mutekar, et al. This is an open access article distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.
Mutekar A, Soni S, Pawar H, Gaikwad P. YodhaAI: An Intelligent Hub for Defence Aspirants. 2025; 2(2):48-53. https://doi.org/10.70968/ijeaca.v2i2.ML101