Adrian Reid walks through a testing framework for trading systems: baseline backtest, analyze best and worst trades, optimize, test each rule's significance, check robustness, then validate out-of-sample. If it holds up in live data, you trade it. If not, you discard it.
I've got a system idea. It's called Q-Bounce, right? But that's irrelevant. It's just a system idea that kind of popped into my head. I want to test it on this universe. So I take an in-sample period of that universe. I run the full process on it. So I run a baseline backtest. I see if it's got any potential. If it has some potential, then I'll look at the best trades and the worst trades. I'll see if I can brainstorm some hypotheses to improve the performance. They may or may not, they may or may not prove true. Then I'll run an optimization process on it to get it as good as possible on that universe. And then I'll do a significance test on each of the rules to make sure every rule is carrying its weight. Then I'll do a robustness test to make sure that the parameters are a stable selection of parameters. And then if that all passes, then I'll do an out-of-sample test and compare in-sample, out-of-sample. If that passes, then I'll think about incubating or trading the system. But if it doesn't pass out a sample, I throw it away. If you want more trading tips from Enlightened Stock Trading, make sure you give this video a like and follow Enlightened Stock Trading so you don't miss the next video. And go to enlightenedstocktrading.com/free to get your free Trader Acceleration Bundle to start improving your trading results today.
