Thread 281753467

this explains why MAL formula to rank anime is biased and buries good shows/ Z formula is fairer

MAL formula:
Weighted Score = (v / (v + m)) * S + (m / (v + m)) * C
S = Average score for the anime/manga
v = Number users giving a score for the anime/manga †
m = Minimum number of scored users required to get a calculated score
C = The mean score across the entire Anime/Manga database

Democracy never had any legitimacy

Who fucking cares.

Ranking is flawed as long as people with less than 115 IQ are allowed to vote.

>>281753573
To the right is the new formula rankings
and it had only 300 anime data

>>281753467 (OP)
I pick up new anime if a MAL review uses the words "creepy" or "Gary stu" to describe the MC, or complains about fan service

>>281753609
forget it it was biased to only pic the top MAL ranked pages. i needed random data to test the formula

Who cares, lol

I unironically think their top manga section is pretty decent. Only ignore meme shit like Chainsaw Man and JJK

>>281753798
you care

All the good stuff has a score between 6 and 7.

>>281753467 (OP)
https://myanimelist.net/apiconfig/references/api/v2#operation/anime_anime_id_get

Example:
https://myanimelist.net/anime/30230/Diamond_no_Ace__Second_Season
>"mean": 8.42,
>"rank": 152,
>"popularity": 1381,
>"num_list_users": 57150,
>"num_scoring_users": 29027,
These numbers differ from what's on the front end (8.30 avg, 80k+ users), so it could be their docs have static data.

>>281753467 (OP)
>maltard
lurk forever

And btw, trusting ChatGPT for math and statistics is absolutely retarded. You shouldn't trust it beyond some shitty weighted average.
Maybe some premium model is better, but most likely not.

Anime & Manga?

>>281753467 (OP)
>MAL
Who asked?