JulesBelveze / time-series-autoencoder

PyTorch Dual-Attention LSTM-Autoencoder For Multivariate Time Series
Apache License 2.0
614 stars 63 forks source link

Not working for many of the tickers #23

Closed Rajmehta123 closed 1 year ago

Rajmehta123 commented 2 years ago

The model worked fine for Netflix ticker but when I run for some other ticker, the model doesn't seem to learn. Or it learns with large errors.

Can you try to predict for the following attached dataset? Also, please attach the config as well.

https://drive.google.com/file/d/18lJk5JouTRomHV2wli99uUL3qWG1N8Vy/view?usp=sharing

image

My configs:

label_col=["close"],  # name of target column
index_col="date",

output_size=1,  # for forecasting

num_epochs=200,
batch_size=64,
lr=3e-4,
reg1=True,
reg2=False,
reg_factor1=1e-4,
reg_factor2=1e-4,
seq_len=20,  # previous timestamps to use
prediction_window=1,  # number of timestamps to forecast
hidden_size_encoder=128,
hidden_size_decoder=128,
input_att=True,
temporal_att=True,
denoising=True,
directions=1,

max_grad_norm=0.1,
gradient_accumulation_steps=1,
logging_steps=100,
lrs_step_size=5000,
JulesBelveze commented 2 years ago

Hey @Rajmehta123 my first attempts were not really successful, I'm getting similar results than you. Will dig a bit deeper.

Can you provide me a link with a description of that dataset please? I don't understand the features at all 😅