Hello, Nice subject whitneybroach. I would like to open it to another field, the one of the multi-objective optimizitation.
Actually random walk, monte carlo can be made "raw", so you extract all statitstic from each run, and finally you can look for the best solution for several objective at the same time... but this is too too and... too ... long time consuming if you have complex system with many parameters. MPC can be good, but I think it is long time computation too ? We got IO too (it use neural networks if i am right), thanks Fred, it can have several goals, but i don't know how it works inside... are all the goals reached during different optimization process (several single-objective optimization) or is it real multi-objective optimization ? Here is a good articles on multi-objective optimization wich review several methods (for gentics, but same can be used for trading i guess) : http://www.calresco <http://www.calresco.org/lucas/pmo.htm> .org/lucas/pmo.htm My question is, are their some people here who try to use some of those another technics of non linear optimisation with multi-objective. Cheers, Mich. ----- Original Message ----- From: whitneybroach To: [EMAIL PROTECTED] <mailto:amibroker%40yahoogroups.com> ps.com Sent: Friday, March 16, 2007 5:12 AM Subject: [amibroker] Detecting data mining bias with modified Monte Carlo procedure While reading David Aronson's book _Evidence-based Technical Analysis_, I stumbled across a modified Monte Carlo permutation (MCP) procedure that compensates for data mining bias, assuming that the "best" permutation of rules was not selected with a directed search. >From Aronson's perspective, this is good news. He views data mining as a useful procedure in the discovery phase of research. Plus, MCP does not require out-of-sample data. Thus it is possible to use more data for mining and still minimize data mining bias in test results. The likely result: fewer false positives for systems that are worthless, and fewer false negatives for systems that are valuable. The paper with discussion and C# code is here: <http://www.evidence <http://www.evidencebasedta.com/MonteDoc12.15.06.pdf> basedta.com/MonteDoc12.15.06.pdf>. Aronson's book site, including a link to Amazon, is: <http://www.evidence <http://www.evidencebasedta.com> basedta.com>. Separately, I'm looking forward to the imminent books from Howard <http://www.quantita <http://www.quantitativetradingsystems.com/> tivetradingsystems.com/> and Ralph Vince <http://tinyurl. <http://tinyurl.com/2os2p7> com/2os2p7>. Not being a user of IO (or other AB add-ons), I have no idea if this MCP approach is already being used in the AB community. It looks interesting to me. MCP appears to require market data and trade data from every run, not simply the trade data. That suggests to me that an AB add-on, rather than a completely external program, would be a more straightforward implementation. Aronson also refers to a patented boostrap procedure that accomplishes much the same thing, White's Reality Check, named for Halbert White, the patent holder. Apparently WRC is not available commercially. Best, __________________________________________________________ Découvrez le Blog heroic Fantaisy d'Eragon! http://eragon- <http://eragon-heroic-fantasy.spaces.live.com/> heroic-fantasy.spaces.live.com/
