System Development Paradigm | Traders Hideout


futures.io - futures trading strategies, market news, trading charts and platforms


Traders Hideout


Discuss day trading practices and futures trading strategies on this forum for all markets. This forum is also for discussing and reviews for brokers, data feeds, and commercial or third party add-ons




 

System Development Paradigm

  #4 (permalink)

Bangkok Thailand
 
 
Posts: 36 since May 2016
Thanks: 15 given, 17 received

I tend to think the same. However, when I read stuff like the quoted part below, from an interview with Jaffray Woodriff in "Hedge Fund Market Wizards "(published 2012) I am not so sure:


Quoting 
- Do you give the same weight to data from the 1980s as data from the 2000s?

Sometimes we give a little more weight to more recent data, but it is amazing how valuable older data still is. The stationarity of the patterns we have uncovered is amazing to me, as I would have expected predictive patterns in markets to change more over the longer term.

- Is the implication then that models donít get dropped even if they perform poorly?

It takes a tremendous amount of deterioration to drop a model. We donít react to the short-term results of a model because the current year performance of any single model is simply not at all predictive of the next yearís performance. What is predictive is how the model performed over the entire 31 years. The extra 3 percent of data provided by the most recent year doesnít make much difference in how a model has performed over the entire training period.


Reply With Quote
The following user says Thank You to TraderWalrus for this post: