A Stochastic Shortest Path Algorithm for Optimizing Spaced Repetition Scheduling

Abstract

Spaced repetition is a mnemonic technique where long-term memory can be efficiently formed by following review schedules. For greater memorization efficiency, spaced repetition schedulers need to model students' long-term memory and optimize the review cost. We have collected 220 million students' memory behavior logs with time-series features and built a memory model with Markov property. Based on the model, we design a spaced repetition scheduler guaranteed to minimize the review cost by a stochastic shortest path algorithm. Experimental results have shown a 12.6% performance improvement over the state-of-the-art methods. The scheduler has been successfully deployed in the online language-learning app MaiMemo to help millions of students.