Global Forecasting Models

In this chapter, we explore various time series forecasting scenarios and learn how to handle them with deep learning. These scenarios include multi-step and multi-output forecasting tasks, and problems involving multiple time series. We’ll cover each of these cases, explaining how to prepare your data, train appropriate neural network models, and validate them.

By the end of this chapter, you should be able to build deep learning forecasting models for different time series datasets. This includes hyperparameter optimization, which is an important stage in model development.

This chapter will guide you through the following recipes:

• Multi-step forecasting with multivariate time series
• Multi-step and multi-output forecasting with multivariate time series
• Preparing multiple time series for a global model
• Training a global LSTM with multiple time series
• Global forecasting models for seasonal time series
• Hyperparameter...