Open stefvra opened 4 years ago
the point is know what you are doing, lstm/rnn output maybe obfuscate by big math/calcs, a classification problem with good interpretation is better when you have a lot of money that isn't your and you need to explain what you are doing, what is good/bad.
bars are never generated simultaniously, unfinished bars are bars that probably will change when the time to close is reached (volume or time based) if it's a problem include a dumb variable with 0/1 to explain that's a open bar (it will be only one by asset, it's not relevant)
others questions are about data modeling, should consider each data before comment
One topic I do not find in the book is sequentializing data (for eg LSTM, RNN...).
I see a few difficulties:
Any toughts or resources on this?