Time Series Prediction: A Non Linear Approach with Neural Networks
MIT License
The purpose of this library is using neural networks to replicate classical
forecast models from the financial industry structurally, like AR(p)
, MA(q)
, ARMA(p, q)
, ARCH(q)
or GARCH(p, q)
, all of which are supported by neuralforecast.
Install the library and run the ARMA example.
git clone https://github.com/maxpumperla/neuralforecast
cd neuralforecast
python setup.py install
python examples/arma.py
AR(p)
)