cenkcorapci / forex-prediction

Comparison of few deep learning models on 15m interval USD/EUR time series data

Forex Prediction

Testing some models on this kaggle data set

Results

Model	Mean Squared Error	Mean Absolute error	Details
Multilayer-GRU	0.0007788221697455181	0.026117904067719574	Notebook
Bi-directional LSTM	6.159634463135478e-05	0.007467821835500006	Notebook

forex-prediction's Issues

bi_rnn_weights is not define

While i try run benchmark code, there is error seem bi_rnn_weights is not create from step above.
I try to use model.save_weights & model.load_weights but not working also.
Could you have a look this part?

---

model.save_weights(filepath) saves the weights of the model as a HDF5 file.
model.load_weights(filepath, by_name=False) loads the weights of the model from a HDF5 file (created by save_weights). By default, the architecture is expected to be unchanged. To load weights into a different architecture (with some layers in common), use by_name=True to load only those layers with the same name.

'Baseline_wights_loc' is not defined

When I am trying to run the Benchmark code of baseline-experiment.ipynb. It shows an error that baseline_wights_loc is not defined.