DeepCAR extends the vanilla DeepAR method by incorporating change points. It is described in the Paper: The DeepCAR Method: Forecasting Time-Series Data That Have Change Points. This repository provides some implementations.
In Simulation_Football_Data.ipynb we give an example with our DeepCAR method using a football dataset. And in Mosum_Football_Data.ipynb you can find the MOSUM method that was applied to this football dataset and provides the change points for our method.
Ayla Jungbluth, Ph.D. student of Mathematical Statistics, Ruhr-University Bochum
Johannes Lederer, Professor of Mathematical Statistics, Ruhr-University Bochum