Loading article...
Loading article...
Stream/Area:
-
Subject:
-
Paper ID:
IJSREM62851
Volume:
10 |
5 |
May 2026
Pages:
1-5
Publication Frequency:
Monthly (12 issues per year)
License:International Journal of Scientific Research in Engineering and Management follows the Creative Commons Attribution 4.0 (CC BY 4.0) License, allowing free use and distribution with proper attribution.

Department of Computer Science and Engineering
Jain (Deemed-to-be) University
Department of Computer Science and Engineering
Jain (Deemed-to-be) University
Department of Computer Science and Engineering
Jain (Deemed-to-be) University
Department of Computer Science and Engineering
Jain (Deemed-to-be) University
India has over 250 million school-going students assessed on the National Council of Educa-tional Research and Training (NCERT) curriculum, yet no mainstream EdTech platform personalises learning at the level of individual chapters, exercises, or page ref-erences within actual textbooks. AdaptIQ V2 addresses this gap by integrating three scientifically validated techniques — the 2-Parameter Logistic Item Response Theory (IRT 2PL) model for real-time ability tracking, the SM-2 Spaced Repetition algorithm for long-term retention scheduling, and Retrieval-Augmented Gen-eration (RAG) with pgvector for textbook-grounded AI tutoring — into a single NCERT-native platform for Classes 6–12. A five-step onboarding wizard captures twelve learner attributes; an adaptive quiz engine selects questions matched to each student’s current ability score (θ), targeting a 65–70% success probability; and a daily study plan generator creates personalised schedules based on weak topic history and available study time. Additional features include a PDF viewer with an inline AI tutor that cites specific NCERT pages, a bilingual English/Hindi interface using official NCERT mathematical terminology, and a GitHub-style streak calendar for gamified engagement. Built on a React 18 + TypeScript frontend, Node.js/Express backend, and Supabase PostgreSQL with pgvector, AdaptIQ V2 delivers the first platform to combine NCERT alignment, IRT-based adaptive difficulty, SM-2 spaced repetition, and a textbook-aware AI tutor in a single production-grade system.
KEYWORDS
AdaptIQ V2 demonstrates that a NCERT-native, AI-driven adaptive learning platform is technically feasible using modern open-source tooling. By anchoring every interaction — question selection, daily plan, AI explanation — to a specific chapter and page in the actual NCERT textbook, AdaptIQ V2 creates a study experience genuinely relevant to a student’s board examination requirements. The integration of IRT 2PL ability tracking, SM-2 spaced repetition, and RAG-powered AI tutoring into a single bilingual platform represents the first of its kind for the Indian school education segment. The system is deployed using Supabase Cloud, OpenRouter, and Vercel/Railway — a fully managed, horizontally scalable stack accessible to any student with a web browser. Future work includes expanding the curriculum to Classes 6–7 and Classes 11–12 (JEE/NEET founda-tion), enabling full pgvector semantic retrieval across all NCERT pages, building parent/teacher dashboards, and implementing a board exam simulation mode with CBSE marking scheme awareness.
[1] F. Baker and S. Kim, Item Response Theory: Parameter Estimation Techniques, 2nd ed. Marcel Dekker, New York, 2004. [2] P. Wozniak, “SuperMemo 2: Optimal Intervals for Spaced Repetition,” Acta Neurobiologiae Experimen-talis, 1994. [3] P. Lewis et al., “Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks,” in Proc. NeurIPS 2020, arXiv:2005.11401. [4] NCERT, Mathematics Textbooks Classes 6–10. National Council of Educational Research and Training, New Delhi, 2024. [5] P. Brusilovsky and E. Millán, “User Models for Adaptive Hypermedia and Adaptive Educational Systems,” in The Adaptive Web, ser. Lecture Notes in Computer Science, vol. 4321. Springer, 2007, pp. 3–53. [6] G. Siemens and P. Long, “Penetrating the Fog: Analyt-ics in Learning and Education,” EDUCAUSE Review, vol. 46, no. 5, pp. 30–40, 2011. [7] J. Hamari, J. Koivisto, and H. Sarsa, “Does Gamification Work? A Literature Review of Empirical Studies on Gamification,” in Proc. 47th Hawaii Int. Conf. System Sciences (HICSS), 2014. [8] K. VanLehn, “The Relative Effectiveness of Human Tutoring, Intelligent Tutoring Systems, and Other Tutor-ing Systems,” Educational Psychologist, vol. 46, no. 4, pp. 197–221, 2011. [9] React Developers, “React Documentation,” Meta Plat-forms Inc. [Online]. Available: https://react.dev. [Ac-cessed: 2025]. [10] Supabase, “Supabase Documentation.” [Online]. Avail-able: https://supabase.com/docs. [Accessed: 2025].
Publication Date
5/8/2026
Peer Review Type
Double-Blind Peer Review
Review Rounds: 2
Documents
Article Views
0
Total views since publication
PDF Downloads
4
Total downloads since publication
Geographic Reach
5
Digital Preservation: This article is permanently archived on Zenodo and complies with all data preservation standards across major indexing platforms.
Plagiarism Screening
This manuscript has been checked for plagiarism using TurnitinPlagiarismChecker software.
Conflict of Interest
The authors declare no conflict of interest related to this research work.
Funding Information
No funding information available for this research.
Related research in the same subject area
Loading similar articles...