Subject: Re: A one-year backtest!
Nagel concluded that because the model was dissecting just 12 months of data, it was simply copying signals that had worked more recently. In other words, it was following a momentum strategy — a well-established trading approach.

... and isn't that what we would expect? A one year backtest trained on 10,000 parameters (most of which are irrelevant or coincident) is as predictive as a one year backtest trained on 10? I mean... that's not even momentum trading.

imagine the cocktail conversation - "I beat the S&P this year by 2% by paying x$$$ for a service that trades based on 10,000 parameters."...

I want the model Bradley Cooper's character used in Limitless.