search

tcloaa / Deep-Portfolio-Theory

Autoencoder framework for portfolio selection (paper published by J. B. Heaton, N. G. Polson, J. H. Witte.)
128 stars 63 forks source link

currently not perfect code #1

Closed tcloaa closed 6 years ago

tcloaa commented 6 years ago

Hi all,

I know that there are some watching this repo. Thank you for your interest! But currently, I am busy with my study and may not have time to re-arrange the code. (or, "fix" the code according to the vague paper.)

Maybe I will spend some time on it in early 2018? Or whoever is interested in this framework is very welcome to contribute!

BrightFeather commented 6 years ago

Are you one of the author? I am very interested in this paper, but I don't understand some ideas. If you are willing to discuss with me, I am willing to contribute. Thanks!

tcloaa commented 6 years ago

@BrightFeather

  1. No, I am not one of the authors. You can reach the original paper from here. Since their codes are proprietary, I have to validate the paper by coding myself.

  2. Sure

tcloaa commented 6 years ago

Hi,

Sorry for the late reply.

I have updated the repo. Please have a look at the new .ipynb file for explanation.

Thanks,

On 9 February 2018 at 20:15, mrshinzzang notifications@github.com wrote:

Please, I need help. I am interested in deep portfolio theory and would like to run the codes with given data(full data). However, I stuck in line

63 of autoencoder.py, that is

autoencoder = load_model('autoencoder.h5') and the error message is OSError: Unable to open file (unable to open file: name = 'autoencoder.h5', errno = 2, error message = 'No such file or directory', flags = 0, o_flags = 0)

How can I get the 'autoencoder.h5'?

— You are receiving this because you authored the thread. Reply to this email directly, view it on GitHub https://github.com/tcloaa/Deep-Portfolio-Theory/issues/1#issuecomment-364418165, or mute the thread https://github.com/notifications/unsubscribe-auth/AIWHWV9Pd-AFXNuplMxTbQxs9IPqEDfzks5tTDbFgaJpZM4QbupP .

-- Best, Phil

LO Tsz Cheung

Department of Computer Science and Engineering The Hong Kong University of Science and Technology Tel: (852) 5516 2962 Email: tcloaa@connect.ust.hk