|
PureBytes Links
Trading Reference Links
|
My research indicates that your friend's success is pure luck. He's headed
for a fall. I have never discovered any credible evidence that the recent
market necessarily resembles the market from four weeks previous. It may
look like common sense, but unfortunatly commen sense can kill you trading.
Read Taleb's latest book, "Fooled by Randomness." Or Bob Buran's writings
about this type of optimizing. My 2 cents.
Regards, Jack.
----- Original Message -----
From: "rascal2" <rascal2@xxxxxxxxx>
To: <omega-list@xxxxxxxxxx>
Sent: Thursday, December 20, 2001 10:25 AM
Subject: Optimization Question
> I trade the S&P futures contract. I understand the pitfalls of
> overoptimization and always optimize any systems I develop on several
> expired contracts before trying them on out-of-range data.
>
> However, I have a friend who used a totally different approach and with
good
> success. He optimizes his (stock trading) system every weekend on data
from
> the previous four weeks. He then uses those settings for the forthcoming
> week, optimizing again the next weekend. He acknowledges that he is
"tuning"
> his system to a specific data set, but does so knowingly with the
> explanation that the market over the next week will most likely resemble
the
> market over the last month. By reoptimizing every weekend with the
previous
> four weeks data, he hopes to keep his system in synch with the market. He
> likens this to developing adaptive indicators.
>
> I know that theoretically this should not work, but in fact it seems to
work
> pretty well. His system consistently turns a better profit with smaller
> drawdowns that it would when optimized over a longer period and then run
> against the same data sets.
>
> I'd be interested in any thoughts anyone might have on this approach.
>
>
>
|