search

jankrepl / deepdow

Portfolio optimization with deep learning.
https://deepdow.readthedocs.io
Apache License 2.0
875 stars 136 forks source link

Example: Learning NumericalMarkowitz parameters #31

Closed jankrepl closed 4 years ago

jankrepl commented 4 years ago

Would be nice to show, how deepdow is able to directly learn or have a network predictor of any input variables of the deepdow.layers.NumericalMarkowitz

It might be a good idea to use real data (i.e. yfinance), however one needs to be careful about the example running too long (both CI and readthedocs need to run it)

robertmartin8 commented 4 years ago

For any code that needs to be run by CI, testing, etc, I really wouldn't recommend calling yfinance live. Better to download the data manually and save it to a resources folder. yfinance sometimes goes down unpredictably (but is generally very good)

jankrepl commented 4 years ago

@robertmartin8 Thanks for the tip!

Personally, I am just afraid of pushing a lot of binary files (or more generally things that are hard to diff like csv) to the github repository. Who knows, maybe in a couple of weeks we realize that the dataset was not the right one.

Did you ever face the same dilemma for PyPortfolioOpt? @robertmartin8