Multi-objective Test Recommendation for Adaptive Learning

Upskilling is a fast-growing segment of the education economy [31]. Yet, there is little algorithmic work that focuses on crafting dedicated strategies to reach high-skill mastery. In this paper, we formalize AdUp, an iterative upskilling problem that combines mastery learning [49] and Zone of Proximal Development [7]. We extend our previous work [9] and design two solutions for AdUp: MOO and MAB. MOO is a multi-objective optimization approach that relies on Hill Climbing to adapt the difficulty of recommended tests to three objectives: learner’s predicted performance, aptitude, and skill gap. MAB is a meta approach based on Multi-Armed Bandits to learn the best combination of objectives to optimize at each iteration. We show how these solutions are combined with two common learner simulation models: BKT (KT-IDEM) [47] and Item Response Theory (IRT) [53]. Our simulation experiments demonstrate the necessity of leveraging all three objectives and the need to adapt the optimization objectives to the learner’s progression ability as MAB offers a higher mastery rate and a better final skill gain than MOO.