euclidjda/deep-quant

Deep learning for forecasting company fundamental data

deep-quant's Issues

the number of features are different between paper and project

There are 20 features in nips paper, but 56 in the project. How to choose them?

Open Dataset Script

Hi, Thank you for providing this to the community. I was wondering if you could share the code that creates the open-dataset.dat file? I am interested in how the fields are generated/obtained. I have access to an online resource for fundamental data but not sure how to prepare the fields and would like to follow along with the script that createst the open-dataset.dat dataset.

Thanks

Replication of LFM paper results

Hi I have access to WRDS account but still cannot obtain results close to paper error rate. I am trying to follow approach described in the paper but still getting much higher MSE, can you specify steps to do it?

About the simulation part

I saw a simulation part in the experiments folder. Is there a readme text about it? Thank you!

Potential multiple prediction

First of all, thanks for sharing this amazing repository. It is a great help for understanding those techniques applied to the finance domain.

I skimmed through the code and I was wondering if there is the possibility to improve the structure of the model and do multiple prediction at the same time. In other words I would be able to test the model on my dataset, outputting the fundamentals at t+1,t+2,t+3 for instance.

To me it looks like the model is able to provide just one single forecast at each timestep, because I don't see such a parameter among the configurations. I am just trying to understand which part of the scripts I should change in order to obtain multiple predictions.

Anyway, thank you again for your great work.

ImportError: No module named configparser

Thank you for making this available,

when i enter: $ python build_data.py --N 10 --exclude_gics 40,45 --filename out.dat --test_mode yes
I get the error "ImportError: No module named configparser"

I have installed configparser and am not sure why I am getting this error

Is it possible to create data without a wrds account?

I found that the .dat file fetched by scripts/build_datfile.py does not appear to contain all of the necessary columns (saleq_ttm for example). Unfortunately, I do not have a wrds account.

Would it be possible to provide an example .dat file that contains the needed columns and example values?

'RuntimeError: The data file data.dat does not exist'

Thanks for good job in advance.
I'm blocked on this issue when trying to 'python deep_quant.py'. So, there's a sample or alternative of it for going further?
If I have to construct it myself, with what format should I follow? Looking like benchmark-ew.dat? Thank you.