This repo contains the code and datasets used for the experiments carried out in the context of the following paper:
Cerqueira, Vitor, Luis Torgo, and Igor Mozetič. "Evaluating time series forecasting models: An empirical study on performance estimation methods." Machine Learning 109.11 (2020): 1997-2028.
The script perfestimation-synthetic.r is only ran for a specific (dataset, algorithm) pair. You need to change those to get the results for a different pair.
For any suggestion or comment on the repo please contact me at [email protected]