Good rule of thumb for embedding for categorical data

[knesgood (Kyle Nesgood)]

This might be of interest.

Size of embedding for categorical variables

So it looks like it changed since I last looked. Previously, it was: def emb_sz_rule(n_cat:int)->int: return min(50, (n_cat//2)+1) Now it looks like it’s the following: def emb_sz_rule(n_cat:int)->int: return min(600, round(1.6 * n_cat**0.56)) I’m not sure of the reason why, but you can dig into the source code here: