Yes. I have built a NNN strategy which trades ETFs. Each ETF in the tradable 
universe is chosen to be a proxy of a sector of the economy. 

The strategy is market-neutral and can best be described as sector rotation 
strategy.

Over seven years the annualized return is 25% and Sharpe ratio is 2.4. It had a 
single drawdawn of 30%, lasting one week when the markets imploded during the 
subprime meltdown.  All other drawdawns were less than 6 %.  The strategy is in 
the market 30% of the time.

It is not an HFT strategy though. It trades only once a day, takes positions 
(or 
not) at the open and closes them at the close. No overnight positions and no 
intraday trading.

I think the same approach can be used for HFT strategy as well.


________________________________
From: Victor Martin <[email protected]>
To: [email protected]
Cc: Astor <[email protected]>
Sent: Fri, February 25, 2011 3:54:04 AM
Subject: Re: [JBookTrader] Poll for new features

Astor, have you backtested successfully any NNN strategy? Can you share its 
results??

cheers


On Fri, Feb 25, 2011 at 4:20 AM, Astor <[email protected]> wrote:

Da, I have built quite a few ANN models. Several of them had been (and I think 
still are) used to manage portfolios with AUM in tens of billions. Let me save 
you some time  - if you are going to optimize thousands of parameters, you will 
most definitely overfit the data. Your model will perform spectacularly in the 
backtest and will fail in actal trading.
>
>I can give you a litany of other problems that you will encounter. You will 
>have 
>no clue whether your forecasts come from densely or sparsely populated sample 
>space, i.e. confidence intervals of your forecasts will vary greatly. When 
>your 
>model fails, you will not know if it is part of normal operation or if there 
>has 
>been a structural shift.
>
>If you are determined to explore non-linear interactions for prediction, you 
>will get much more consistent and much more intuitive results using N-nearest 
>neighbor algorithm. NNN has no parameters to optimize, requires no training 
>and can be updated in real time - which is very important for HFT.  As long as 
>your original hypothesis for your model makes sense, you will be able to 
>understand the basis for the predictions.
>
>Good luck.
>
>
>
________________________________
From: Da Xu <[email protected]>
>To: [email protected]
>Sent: Thu, February 24, 2011 6:41:18 PM 
>
>Subject: Re: [JBookTrader] Poll for new features
>
>
>
>As I posted before, I woud like to develop artificial neural networks strategy 
>on JBT. We have to add thousands of parameters and change the optimization 
>class. I have been focusing on this project for a couple of months.  Are there 
>anyone that is interested in ANN strategy?
>
>Da
>
>
>
>On Wed, Feb 23, 2011 at 3:19 PM, nonlinear <[email protected]> wrote:
>
>Do JBT users have a "wish list" for the new JBT features/functionality? If so, 
>please post them here.
>>-- 
>>You received this message because you are subscribed to the Google Groups 
>>"JBookTrader" group.
>>To post to this group, send email to [email protected].
>>To unsubscribe from this group, send email to 
>>[email protected].
>>For more options, visit this group at 
>>http://groups.google.com/group/jbooktrader?hl=en.
>>
>-- 
>You received this message because you are subscribed to the Google Groups 
>"JBookTrader" group.
>To post to this group, send email to [email protected].
>To unsubscribe from this group, send email to 
>[email protected].
>For more options, visit this group at 
>http://groups.google.com/group/jbooktrader?hl=en.
>
>
>-- 
>You received this message because you are subscribed to the Google Groups 
>"JBookTrader" group.
>To post to this group, send email to [email protected].
>To unsubscribe from this group, send email to 
>[email protected].
>For more options, visit this group at 
>http://groups.google.com/group/jbooktrader?hl=en.
>
-- 
You received this message because you are subscribed to the Google Groups 
"JBookTrader" group.
To post to this group, send email to [email protected].
To unsubscribe from this group, send email to 
[email protected].
For more options, visit this group at 
http://groups.google.com/group/jbooktrader?hl=en.



      

-- 
You received this message because you are subscribed to the Google Groups 
"JBookTrader" group.
To post to this group, send email to [email protected].
To unsubscribe from this group, send email to 
[email protected].
For more options, visit this group at 
http://groups.google.com/group/jbooktrader?hl=en.

Reply via email to