NeuralForecast

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.

Getting started

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

Time-series models and their neural network counterparts

Auto-regressive models (AR(p))