Diffusion Variational Autoencoder (D-Va)

This repository contains the code for "Diffusion Variational Autoencoder for Tackling Stochasticity in Multi-Step Regression Stock Price Prediction" [Paper].

Environment

Python 3.8

For the required dependencies, see requirements.txt.

Run

There are 12 experiments in the paper.

Use sh run.sh in your terminal to run all of them, or you can run each command from the file separately.

Citation

If you find this repository useful, please cite our paper.

@inproceedings{koa2023diffusion,
  title={Diffusion Variational Autoencoder for Tackling Stochasticity in Multi-Step Regression Stock Price Prediction},
  author={Koa, Kelvin J.L. and Ma, Yunshan and Ng, Ritchie and Chua, Tat-Seng},
  booktitle={Proceedings of the 32nd ACM International Conference on Information and Knowledge Management},
  pages={1087–1096},
  year={2023}
}

Acknowledgement

We appreciate the following GitHub repositories a lot for their valuable code base:

https://github.com/PaddlePaddle/PaddleSpatial/tree/main/research/D3VAE

https://github.com/NVlabs/NVAE