Advanced Forecasting with Python: With State-of-the-Art-Models Including LSTMs, Facebook’s Prophet, and Amazon’s DeepAR

© The Author(s), under exclusive license to APress Media, LLC, part of Springer Nature 2021

J. KorstanjeAdvanced Forecasting with Pythonhttps://doi.org/10.1007/978-1-4842-7150-6_21

21. Model Selection

Joos Korstanje¹  

(1)

Maisons Alfort, France

 

In the last 18 chapters, you’ve seen a long list of machine learning models that can be used for forecasting. In this chapter, you’ll find some final reflections on how to decide which of the models to use for your practical use cases.

Model Selection Based on Metrics

The book started with an overview of model metrics. Throughout the different chapters, a number of model benchmarks have been done based on R2 scores. This was done firstly in Chapter 15, where XGBoost performances were benchmarked against LightGBM ...