richards0268 / autoencoder-asset-pricing-models

Reimplementation of Autoencoder Asset Pricing Models (GKX, 2019)

Hey! Nice to see you.

📊 this week I spent my time on:

Python          8 hrs 45 mins   ████████████████████████▓   98.84 %
CSV             5 mins          ▒░░░░░░░░░░░░░░░░░░░░░░░░   01.05 %
Objective-C++   0 secs          ░░░░░░░░░░░░░░░░░░░░░░░░░   00.06 %
Other           0 secs          ░░░░░░░░░░░░░░░░░░░░░░░░░   00.02 %
JSON            0 secs          ░░░░░░░░░░░░░░░░░░░░░░░░░   00.02 %

🤗 I’m currently pursuing my double bachelors degree of computer science and finance at Tsinghua University, Beijing.

🎯 I’m interested in Machine Learning, Deep Learning and their applications in quantitative finance.

⌨ I'm frequently coding in

⚙ I'm continually using

🛸 I'm familiar with

🚀 My Contributions

autoencoder-asset-pricing-models's Issues

Is there a missing file mon_list.pkl?

Add 2023-2024 dataframe

Is this possible to have the data up-to-date with 2023-24 data ?

Thanks you a lot for the work

About the method of preprocessing

From the data_prepare.py I find that the managed portfolio is constructed using the classical method, i.e., long the first decile and short the last decile. However, the preprocessing method of GKX (2021) is a linear transformation of returns (see equation (16) in the original paper). I wonder if it is your simple choice for convenience, or you just find the classical method is better than the authors' method?