An Educational System for Personalized Teacher Recommendation in K-12 Online Classrooms
This addresses the practical issue of efficient teacher-student matching for online education platforms, though it appears incremental as it builds on existing recommender system concepts.
The paper tackles the problem of teacher recommendation in K-12 online one-on-one classrooms by proposing a system with modules for pseudo matching scores, ranking, novelty boosting, and diversity, which reduces student-teacher matching attempts from 7.22 to 3.09 in a five-month observation.
In this paper, we propose a simple yet effective solution to build practical teacher recommender systems for online one-on-one classes. Our system consists of (1) a pseudo matching score module that provides reliable training labels; (2) a ranking model that scores every candidate teacher; (3) a novelty boosting module that gives additional opportunities to new teachers; and (4) a diversity metric that guardrails the recommended results to reduce the chance of collision. Offline experimental results show that our approach outperforms a wide range of baselines. Furthermore, we show that our approach is able to reduce the number of student-teacher matching attempts from 7.22 to 3.09 in a five-month observation on a third-party online education platform.