He is still pushing that old clunker of an optimizer very hard http://www.elitetrader.com/vb/showthread.php?s=&postid=2166827&highlight=stratasearch#post2166827
He is still pushing that combinatorial optimizer http://www.elitetrader.com/vb/showthread.php?s=&postid=2166827&highlight=stratasearch#post2166827
He has pushed this random optimizer before http://www.elitetrader.com/vb/showthread.php?s=&postid=2166827&highlight=stratasearch#post2166827
Yep it is very brute force .... slow .... it has been running for several hours but at least I am starting to get meaningful & enlightening results. I have also tried Neuroshell (which seemed useless) and APS (which was useful but not flexible). What would you recommend? I know there is another package out there, but it cost like $40k, I forgot the name.
Quick reply... Random entries and random datas are 2 different things. Random Data is "Similar" to saying that you're dealing with a (pseudo-)Random Cause. Random Entry / Random Exits is "Similar" to saying that you're dealing with semi-random reactions to the data. Random exits with well thought out entries can be profitable. Look at mean reversion. You enter into a Delta3+ and probabilistic outcome will be positive (considering that the exit is random... you'll have assess the value by the probability of prices returning to the mean value) you'll have a profitable exit. ...
Can you clarify your 2nd rule? What do you mean by "High"? if (C > R) { Rand() > 0.666 ? y = "High" : y = ???? }
True enlightening will come to you when you understand what randonly optimized systems are and how much damage they can do to you.
the market is nothing more than a reflection of human psychology/emotions. if you believe human psychology/emotion are (pseudo-) random, then you can use (pseudo-)random data to test your strategy.
For the purposes of this thread, I think all will agree that randomly optimizing systems on random data (or even price data) is useless. But for my purposes - I am using calculated datasets which may actually contain an edge.
The best way to explain this is through an example. Suppose we have price data that is normally distributed between 100 and 200. In excel this function would be RANDBETWEEN(100,200) or something similar. One turn = one change in price. 1st turn we have an R = 123 and C = 155. C is now a "high" value. 2nd turn we have an R = 190 and C = 156. C is now a "Low" value. 3rd turn we have an R = 177 and C = 157. C is now a "Low" value. 4th turn etc etc... Each turn in this case will either have a right or a wrong outcome depending on the value of C(t+1). t=turn. In the case above R(1) < C(1) -> C(1) = high. C(1) < C(2) = 156 -> "wrong" R(2) > C(2) -> C(2) = low. C(2) < C(3) = 157 -> "right" R(3) > C(3) -> C(3) = low. C(3) < C(4) = 158 -> "right" etc etc... If one repeats this process for N - trials, the probability of being "right" = 66%. This is a classic gambling exercise. There are some interesting characteristics of this process that some here may have seen before. One is that it doesn't matter if C(1),C(2),C(3)... is continuous or not. Second, the random distribution used for comparison is *independent* of C(t). We now have a way to determine if the next closing price will be higher or lower with a 66% accuracy. So, how do we create a trading rule? Mike