[Feature Request] Add another condition to the outlier filter about fsrs-optimizer HOT 4 CLOSED

It can be useful for some users but it can be detrimental for others (especially those who are using Anki for more than 5-10 years).

perhaps there is already something similar.

No, there isn't.

from fsrs-optimizer.

Fair point. Then how about this:
leech_threshold = max(10, percentile(leeches, 0.95))
reps_threshold = max(40, percentile(reps, 0.95))
This is more adaptive. For users with young collections, the thresholds will be 10 and 40. For users with old collections, thresholds will be higher. Both the number of leeches and the number of reviews need to exceed the threshold in order for that card to be excluded from optimization.

from fsrs-optimizer.

@user1823 @L-M-Sherlock maybe we should also remove "anti-leeches" - cards with no Again ratings. For example, remove cards with n(Again)=0 and n(reviews)>10. Just like leeches, they do not follow the usual memory patterns, just in a different way.
EDIT: actually no, that wouldn't work. Assuming 90% probability of recall (for example), there is a 0.9^10=0.349 chance that a user would get a card right 10 times in a row. So we would remove way too many cards. The number of reviews needed to identify "anti-leeches" would be way too high, like 30.
Still, my suggestion about the leech threshold in my previous comment sounds good.

from fsrs-optimizer.

Users can filter out those cards via specific query: https://docs.ankiweb.net/searching.html#card-properties

from fsrs-optimizer.