Adaptive assessment system improves personalized question routing and scoring
MARS: A Momentum-Aware Adaptive Rating System for Personalized Assessment
Computers and SocietyMachine Learning
Summary
Adaptive assessment systems customize tests to a learner's level by estimating their skills and choosing appropriate questions. The authors present MARS, a new system that updates learner ratings more smoothly by considering question difficulty, answer quality, and how skills change over time. MARS also plans test questions to fit within a fixed time and penalizes wrong answers. When tested on student data and simulations, MARS improved overall test scores and reduced cases where tests ran over time, showing it can work well in real-world learning settings.
What this means in practice
- •For online education platforms: Integrate MARS to personalize assessments that select questions fitting within strict test durations, improving score efficiency and fairness.$Commercial implications: Makes possible real-time, personalized assessment products that optimize question selection under time and scoring constraints.
- •For corporate training teams: Use MARS to adapt employee skill evaluations dynamically and interpretably while controlling test length and scoring impact.
Authors
Vikrant Sahu, Khethavath Sunil Naik, Gagan Raj Gupta
Abstract
Adaptive assessment systems personalize learning by estimating learner proficiency and recommending suitable questions. However, many existing approaches rely on fixed difficulty labels, static rating updates, or black-box prediction models that provide limited control over rating stability, interpretability, and time-constrained routing. This paper proposes MARS, a Momentum-Aware Adaptive Rating System for interpretable adaptive assessment. MARS represents the question bank as a directed weighted knowledge graph and updates learner proficiency using dynamic rating sensitivity, response quality, and momentum-aware learner velocity. We also formulate a time-budgeted mark-maximization objective in which the policy selects questions within a fixed test duration under negative marking. Experiments on ASSISTments 2009 and MARS-SimExam evaluate MARS for prediction, rating stability, and adaptive routing. Results show that MARS provides smoother rating updates than Fixed Elo and achieves the highest score under time-budgeted negative-marking routing, improving the total score by 8.09 over the strongest baseline and reducing overtime violations from 50% to 5.6%. These results suggest that MARS is suitable for real-time, interpretable, and deployment-friendly adaptive assessment.