Hello, thanks for your posts I’ve been enjoying thinking about what you are saying.
Just to play devils advocate on this point, and help myself understand a little bit, is it unreasonable to say they have already paid for the MM with historical payouts? If MMC is 0, doesn’t that mean the is no reason to incorporate the user’s signal into the next version of the MM and the MM would remain unchanged if this were the only contributed signal?
Don’t get me wrong, I’m devastated that Corr multiplier is 0.5, and that MMC is 4x higher, it might be the death of my participation, as I was just getting my Classic models to produce some stable signals, and don’t want to “start over”. But, I don’t see the fundamental problem with the team having “bought” the current state of the meta-model with the payouts that have run the tournament over the past years, and now consider this model the bare minimum to be able to improve upon be able to continue in the tournament.
I don’t think it’s a user-friendly way to move forward, and in fact I hate it; it says to me “we’re using your predictions only for as long as we need you,” which is something I feared before I started participating. Just trying to understand if there’s something I’m missing with respect to fairness towards us.
is it unreasonable to say they have already paid for the MM with historical payouts?
I believe it is unreasonable. The MM has to be built at every round, so Numerai continuously needs the users’ models. But without reward the users would stop submitting.
Just to be clear, I like the current tournament and MMC is much better than TC. I don’t even want the models to be rewarded for predictions that are either useless or detrimental to the hedge fund (if the fund doesn’t go well, everybody lose).
My only concern is that MMC and TC do not take into consideration the effort and risk (!) of building the MM and Numerai doesn’t seem to care much about that. Numerai even considered going for 0 CORR multiplier. That is what worries me.
the switch to MMC will cause an outflow of bad performers which will significantly increase the payout factor
But decrease the payout.
What Numerai neglects to acknowledge is that when the outflow of (likely good) performers happens, they cash out. When they cash out, they sell the crypto and as such, influence the market.
In other words, if you extract a benchmark (e.g. short top cryptos or just ETH and buy NMR), you’ll be at a loss. Because the monetary payout “factor” has decreased, not increased due to the NMR impact on payouts.
After carefully observing both MMC and CORA20V2 results, it seems that they are closely aligned. If this observation holds true, it prompts the question: why maintain two separate indicators for scoring? A similar pattern is also evident in the signals.