Hello, I started using the backtester some time ago, now I see that you added some option for preserving the state, and another version optimized for machine learning. Honestly I am a little bit confused, which version should I use? Is there a preferred choice?
support last edited by
@jeppe_and Hi, there are 4 options for backtesting:
- processing all data in one pass. Very fast but you risk to overfit (by taking a global average for example);
- processing all data in many passes using the built-in backtester;
- same, but preserving the state at each iteration; for example, you can use the weights of yesterday to fix the weights today. In this case submission will take longer as parallelization is not possible;
- if yo use machine learning methods and you need to retrain your model periodically, you can use the ml extension for the call to the backtester.