Sequentializing data

[stefvra]

One topic I do not find in the book is sequentializing data (for eg LSTM, RNN...).

I see a few difficulties:

• When using information driven bars on multiple symbols, the bars will not be generated simultaniously. So when exactly to do the sequentializing? What to do with unfinished bars?
• Sequentializing introduces a large overlap between samples. I assume this also needs to be taken into account for sequential bootstrapping and sample weights?

Any toughts or resources on this?

[rspadim]

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