lancopku/cgm

Code for IJCAI 2021 main conference paper "Long-term, Short-term and Sudden Event: Trading Volume Movement Prediction with Graph-based Multi-view Modeling"

CGM

This is the code of our IJCAI-21 paper: Long-term, Short-term and Sudden Event: Trading Volume Movement Prediction with Graph-based Multi-view Modeling. . The original news data is shared at https://pan.baidu.com/s/1zTHKy54DOu0p9_fa4s-JVg The extraction code is：elj8.

Structure of the source code

src_classification/regression 
    -graph 
        -correlation.py 
        -file.py 
        -file_overnight.py (processing data)
        -utils.py 
    -models 
        -attention.py 
        -glstm.py 
        -cgm.py (our model)
        -slstm.py 
        -transformer.py 
    -criterion.py 
    -Data.py 
    -dcca.py
    -file.py 
    -lr_scheduler.py 
    -optims.py 
    -train.py (main process)
    -utils.py 

Shell scripts for training CGM

for volume movement classification task

CUDA_VISIBLE_DEVICES=0 python3 src_classification/train.py -config config_classification.yaml -verbose -log graph_dcca_classification

for volume movement regression task

CUDA_VISIBLE_DEVICES=0 python3 src_regression/train.py -config config_regression.yaml -verbose -log graph_dcca_regression

Citation

If you use the above code for your research, please cite our paper:

@inproceedings{zhao2021longterm,
  title={Long-term, Short-term and Sudden Event: Trading Volume Movement Prediction with Graph-based Multi-view Modeling},
  author={Liang Zhao, Wei Li, Ruihan Bao, Keiko Harimoto, Yunfang Wu and Xu Sun},
  booktitle={Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence, {IJCAI} 2021, Montreal, Canada, August 21-26, 2021},
  year={2021}}

cgm's Issues

请问数据集公开吗？怎么获得呢？

RT

Historical stock data missing

Dear authors,

Thanks for your great work!

I am trying to run this model, but I find that there is a lack of historical stock data. And the folder 'data' mentioned in 'config_classification.yaml' is missing. Could you please provide the relevant data and files?

Thank you!

question regarding missing data in prediction phase

Hi!

Appreciate for sharing such greate work!

My concern regarding to the pratical usability of this whole pipeline is: if you select a stock universe i.e., stocks in the CSI300 index, or just simply select n stocks (doesn't really matter), to train the model, then how is the model gonna functioning well (do the right prediction) if some stocks quit the market, or stopped trading for a short period? From my understanding the vertices and edges cannot be missing, or nan?