itresearch

In general I would say that if you preprocess your dataset and then you split into train/test, you train the model and you check the results in the test part,...

@timothyyu absolutely right! You should apply wavelet and any kind of preprocessing separately on train and test dataset. I am also working on this topic and I recommend you the...

> Here's an example of applying the wavelet transform to the first two `train-validate-test` splits of the `csci300 index data` : >  ok @timothyyu , does this example come...

Hi @timothyyu thanks for your reply, let me check the code. One more question: how do you apply scaling? Also to scaling you should apply the same concept. Validate and...

Hi @timothyyu , I had a look to autoencoder.py and model.py. You basically don't use embedding. So you basically denoise all your test dataset and then use a value from...

@az13js I believe it is because log return it is used during preprocessing

@gainskills was this implemented?

Thanks ShihHauTan, what does 0.5 stand for? Is it PIPS or percentage? How are trading costs calculated?

@ShihHauTan one more question: walk-forward testing for machine learning models, is it implementable in finmarketpy ?

Thanks @ShihHauTan , sorry for so many questions but, before dedicating a lot of time and finally find that is not be feasible, I'd prefer to ask. What I want...