Direct strategy
The direct strategy, also called the independent strategy, is a popular strategy in forecasting using ML. This involves forecasting each horizon independently of each other. Let’s look at the diagram first:
Figure 17.3 – Direct strategy for multi-step forecasting
Next, let’s discuss the regimes in detail.
Training regime
Under the direct strategy, we train 
different models, which take in the same window function but are trained to predict different timesteps in the forecast horizon. Therefore, we are learning a separate set of parameters, one for each timestep in the horizon, such that all the models combined learn a direct and independent mapping from the window, 
, to the forecast horizon, 
.
This strategy has gained ground along with the popularity of ML-based time series forecasting. From the ML context, we can practically implement it in two ways:
- Shifting targets – Each model in the horizon is...
