Bailout

The Renaissance common-sense test

By Felix Salmon

Robert Frey, formerly of Renaissance Technologies, has a new Fund of Hedge Funds, and good for him. He also lifts the kimono ever so slightly on how Renaissance works:

At Renaissance, models had to meet four principles, says Mr Frey. These were (and maybe still are): simplicity ? ?don?t make it more complicated than it needs to be?; commonality ? ?make it as broad as possible?; stability ? ?models you have to readjust constantly probably aren?t as good as ones that stand the test of time?; and rationality ? ?it can?t just be statistically valid?. You have to employ reason to identify a statistically significant but spurious pattern.

I think that quants in general would pay lip service to these principles, but they wouldn’t necessarily give them such a central importance. Of course, the proof of the pudding is in the eating: what counts as simple and stable for Renaissance’s purposes would probably be considered nothing of the thought by mere mortals.

But I do like the final “common sense” test. “This strategy works, but I don’t know why” is always a bad way of trying to make money, because it’s very likely to be a statistical fluke. Ideally, of course, there would be a sequencing test too: it’s not enough to come up with a strategy which works and then try to work out why. You have to start with a theory of why a certain strategy might work, and then test it. I wonder whether Renaissance does that.

Full post as published by Macroprudential on June 14, 2010 (boomark / email).