Challenge 5 - Hyperparameter Tuning

Marco Zanotti

Content

This challenge is about hyperparameter tuning (Module 2 Lecture 2.3).

The purpose of this challenge is to test your ability to optimize sequential and non-sequential models for time series forecasting.

Requirements

You are required to produce a fully reproducible notebook report explaining all the steps that takes you towards the optimization of a sequential model and a non-sequential model.

You are free to apply the feature sets you created during Challenge 1.

Data

Challenge dataset contains an hourly time series of the M4 competition.