Focal Interest
Focal Interest
AI Summary of Peer-Reviewed Research

This page presents an AI-generated summary of a published research paper. The original authors did not write or review this article. [See full disclosure ↓]

Publishing process signals: MODERATE — reflects the venue and review process. — venue and review process.

Thompson sampling improved exercise recommendations for learner skill gain

A student wearing glasses sits on a teal-colored couch or chair, viewed from behind over their right shoulder, working on a laptop computer in a bright, modern home interior with white shelving visible in the background.
Research area:Artificial intelligenceManagement Science and Operations ResearchOnline Learning and Analytics

What the study found

The study found that a contextual Thompson sampling approach for educational recommendations can suggest exercises associated with greater learner skill improvement. The method also adapted effectively to differences across learners.

Why the authors say this matters

The authors conclude that the framework enables personalized practice at scale. They also say it can highlight exercises with consistently strong learning value and help instructors identify learners who may benefit from additional support.

What the researchers tested

The researchers introduced a method that generates personalized sequences of exercises by choosing, at each step, the exercise most likely to advance a learner’s understanding of a targeted skill. The method uses information about the learner and their past performance, and progress is measured as the change in estimated skill level before and after each exercise.

What worked and what didn't

Using data from an online mathematics tutoring platform, the approach recommended exercises associated with greater skill improvement. It also adapted effectively across learners. The abstract does not describe any clearly reported failures or comparisons that did not work.

What to keep in mind

The available summary does not describe detailed limitations, and the findings are based on data from an online mathematics tutoring platform. The abstract does not provide information about performance outside this setting.

Key points

  • The study found that a contextual Thompson sampling approach recommended exercises associated with greater skill improvement.
  • The method adapted effectively to differences across learners.
  • Progress was measured as the change in estimated skill level before and after each exercise.
  • The authors say the framework can enable personalized practice at scale.
  • The abstract does not describe detailed limitations or performance beyond the online mathematics tutoring setting.

Disclosure

Research title:
Thompson sampling improved exercise recommendations for learner skill gain
Authors:
Lukas De Kerpel, Arthur Thuy, Dries F. Benoit
Publication date:
2026-03-10
DOI:
10.1287/ited.2025.0174
OpenAlex record:
View
AI provenance: This post was generated by OpenAI. The original authors did not write or review this post.

More posts