FSRS, developed by Jarrett Ye, is a modern spaced repetition algorithm that aims to improve memory retention and schedule reviews more efficiently than Anki’s SM2 algorithm. The algorithm calculates optimal intervals between reviews based on the probability of recalling a card. It is based on the “Three Component Model of Memory,” which includes retrievability, stability, and difficulty. FSRS analyzes the user’s review history using machine learning to estimate the values for retrievability, stability, and difficulty. Users can adjust the scheduling by choosing a desired retention value. FSRS requires fewer reviews compared to Anki’s default algorithm and is better at scheduling cards with delayed reviews. The FSRS4Anki Helper add-on provides additional features.
https://github.com/open-spaced-repetition/fsrs4anki/wiki/ABC-of-FSRS