Author Affiliations
[1] Associate Professor/CSE, PMC TECH, Hosur, India
[2] [3] [4] Department of Computer Science and Engineering, PMC TECH, Hosur, India
Abstract
The rapid evolution of technical recruitment has placed competitive programming (CP) at the forefront of skill evaluation. However, the sheer volume of available problems often leads to “cognitive overload” and inefficient learning paths. This paper introduces an AI-driven web application that replaces static syllabi with a dynamic, rule-based adaptive learning path. By utilizing a diagnostic engine to calculate granular skill scores across eleven algorithmic domains, the system generates a personalized roadmap. We present a mathematical model for skill estimation and a feedback-loop mechanism that adjusts difficulty based on real-time accuracy. Experimental results indicate a significant reduction in time-to mastery compared to traditional linear roadmaps.
Index Terms—Adaptive Learning, Rule-based AI, Competitive Programming, Flask, Pedagogical Engineering, Data Structures.
How to Cite This Article
Dr. Gul Shaira Banu Jahangeer, Prithika V, Pavithra G, Rithika S (2026). A Rule-Based Adaptive Learning Framework for Competitive Programming. International Journal of Innovative Research in Multidisciplinary Education & Technology (IJIRMET), 11(3).