Instability in Annualized Gain %s during backtesting
Author: GriffinX2018
Creation Date: 5/23/2019 3:44 AM
profile picture

GriffinX2018

#1
Dear Eugene and/or Cone,

I am having an issue while backtesting strategies. While keeping params (rules) the same I get different
Annualized Gain % numbers each time I run the backtest. I am not using any rules that generate an in/out of sample data nor is there any optimization method such as Monte Carlo or neural nets.

Any thoughts on this problem?
Thanks, Richard
profile picture

Eugene

#2
Dear Richard,

I'm pretty sure it's not just Annualized Gain % number that is unstable but many other performance metrics. Since the WealthSignals Publisher (which you're using) doesn't accept Raw Profit backtests, it must happen in Portfolio Simulation mode. And there's an explanation and two workarounds in the Wiki FAQ which I encourage you to check out:

Every time I run a Strategy I get a different result. What am I missing?
This website uses cookies to improve your experience. We'll assume you're ok with that, but you can opt-out if you wish (Read more).