jpb Veteran   Posts: 168 Joined: 5/11/2005 Location: Brown Deer, WI  User Profile | Mark, This is awesome! (and by the way, the spreadsheet worked fine for me) I'm going to compare it to what I've been doing with Pivot Tables but I already see that you are doing some things here that I couldn't possibly do (or don't know how to) with pivot tables. I continue to learn more with each post of yours that I read. I do have one question. You stated: In particular, if you just input the trades already selected using ATM’s filtering and ranking, then you will definitely be curve fitting. However, if you input a large, representative sample of a variety of diverse trades over time then this can definitely help find robust combinations that ATM will then refine. I take it that you mean, because we took as many trades as possible (using the $1 million, 2% allocation, and 100 long and short), the strategies had to stand on their own (no ATM optimization -- only the definition of the market state really came into play). And because of this and the size of the population over a long period of time, we can find stronger strategies to use with each market state. Then if we activate only those strategies for the given market state, we will effectively be improving our results while minimizing any curve fitting that may be leading us into a false sense of optimistic performance. Did I get that right? Thanks, Jeff B. [Edited by jpb on 8/13/2018 2:10 PM] | |
