Conversation

This Tweet was deleted by the Tweet author. Learn more
This Tweet was deleted by the Tweet author. Learn more
This Tweet was deleted by the Tweet author. Learn more
Replying to and
Kelly Criterion useful for random variables that follow normal distribution (dice) or log-normal distribution. For fat-tailed distributed random variables (bitcoin or stocks returns) applying Kelly Criterion is a suicide, especially with leverage. Lol.
Image
1
2
Depends on many factors: leverage, volatility, price return distribution, strategy... Fractional Kelly (betting a fixed fraction of the amount) with strictly no leverage strategies can reduce volatility and protect against non-deterministic errors.
Quote Tweet
If you invested $100 per day (not regular) in #bitcoin. Buy and hold since Aug 2017 till now you would got ~100% profit. Here’s what Harry Markowitz would tell you to do if he was a financial advisor and you were a client: rebalance when your DCA strategy makes ~50-100% profit.
Image