- An attempt to use deep learning for the Two Sigma Financial Modeling Challenge.
- The results do not look promising: a validation R score of -0.0024 after 4 epochs.
-
Download and install neon 1.8.1
git clone https://github.com/NervanaSystems/neon.git cd neon git checkout v1.8.1 make source .venv/bin/activate -
Verify neon installation
Make sure that this command does not result in any errors:
./examples/mnist_mlp.py -e1 -
Install prerequisites
pip install pandas sklearn -
Download the data files from Kaggle:
Save all files to a directory (referred to as /path/to/data below) and unzip the .zip file.
-
Clone this repository
git clone https://github.com/anlthms/fmc-2017.git cd fmc-2017 -
Train a model and validate
./run.py -w </path/to/data> -e 4 -r 0 -quick
- Omit
-quickto use the entire data for training and validation.