Hi Jiacopel,
I try to answer your questions:
- There is no defined rule for the frequency of retraining, ward suggest to retrain whenever the prediction result is started going wrong. If based on your fix PS/TS you have experience that your model started to decreasing in profit after minimum 1 week-2 weeks, then you shoud retaring your model afetr 1 week.
- NS has facility to set the training and OOS, you may change in Trading strategy parameters, Date tab then specify the starting date of training & OOS. Its better to learn properly your software..
Cheers
I try to answer your questions:
- There is no defined rule for the frequency of retraining, ward suggest to retrain whenever the prediction result is started going wrong. If based on your fix PS/TS you have experience that your model started to decreasing in profit after minimum 1 week-2 weeks, then you shoud retaring your model afetr 1 week.
- NS has facility to set the training and OOS, you may change in Trading strategy parameters, Date tab then specify the starting date of training & OOS. Its better to learn properly your software..
Cheers
What is generally regarded as the ideal frequency of reoptimization in Neuroshell? Should I optimize on the previous 200 bars and trade 100 bars OOS? Unfortunately, NS does not allow me to set both a date range for optimization and a date range for OOS testing. It automatically chooses the remaining bars after the optimization period for OOS testing. In order to test, I need separate data sets for each date range, which is a bit of a hassle.