Just a reminder that the Kelly formula gives you the optimal bet size IF you buy its assumptions; if you don't then it's not optimal. For example, if you don't have what's called "iso-elastic" utility, then the Kelly formula is not optimal. If you don't have "constant relative risk aversion", then the Kelly formula is not optimal. Ganch discussed all this
here, and (in typical fashion) made his point with a very cute non-mathematical statement:
"What's optimal for me (a butterscotch and banana lover), may very well be
suboptimal for you (a chocolate and vanilla lover)."
So let's not go overboard with the Kelly love.