replacementAI
replacementAI
I believe I heard/read some where that they ran the model 5 times and averaged the results.
Thats good to hear @MickyDowns, could you share the results on the performances of different time candles?
Is there an update regarding the above?
https://github.com/fracdiff/fracdiff/pull/170
https://lightgbm.readthedocs.io/en/latest/Parameters.html#max_bin You can decrease the max_bin parameters, it defaults to 255 bins, the lower the faster https://lightgbm.readthedocs.io/en/latest/Parameters.html#use_quantized_grad You can also enable quantization, it defaults to 4, the lower the faster
Lmk if any changes need to be made @simaki. Thanks for taking a look 😃
Btw this is how it looks like https://github.com/replacementAI/fracdiff/blob/main/examples/Frac%20Diff%20Example.ipynb
I think in block 7, I need to elaborate that the frac diff model outperforms the 3 other models. I also want to reduce the search space window to 147...
I still need some time to work on this, Ive been a bit busy
@simaki, sorry for the late commit, I've finished up the example. The target is the log return of a L/S portfolio where ETH is long and BTC is short. I...