Expertium

I tried this: ``` if small_rating in rating_stability and big_rating in rating_stability: if rating_stability[small_rating] > rating_stability[big_rating]: rating_stability[big_rating], rating_stability[small_rating] = rating_stability[small_rating], rating_stability[big_rating] ``` It made results worse. 

@dae I also have a request: include both card ID and note ID. I have an idea how to account for reviews of siblings, though it will probably only work...

@dae just a reminder about the dataset. I know that changing the way Anki works to make it so that FSRS can access the history of card B while the...

@dae Once you do decide to make a new dataset, please take this into consideration: https://forums.ankiweb.net/t/question-how-difficult-would-it-be-to-give-fsrs-access-to-certain-info/47645 So ideally, the new dataset would have the following new features: 1) `PresetName` and...

Btw @dae, I tried adding the number of hours since `day_starts_at` and the number of reviews done today before the next review to FSRS to calculate fatigue, but it didn't...

@Gilfaro hey, just wanted to let you know that we're done benchmarking new algos and re-benchmarking old ones, but it's not too late (it's never too late, for that matter)...

Interesting! Could you share the code? Funnily enough, less than 2 hours ago I said "There seems to be some kind of curse surrounding people who want to add decision...

Can you make a decision tree based model that doesn't borrow anything from FSRS? To be honest, that's what I was expecting.

Then how about HLR-catboost?

That's a huge improvement! ~~@L-M-Sherlock I think we should include HLR-catboost in the benchmark.~~ I have 2 questions: 1) How many parameters does it have? 2) Can you explain how...