chapter ten
This chapter covers
- Making accurate predictions for the daily traffic volume to a blog’s website
- Designing a robust protocol for model comparison and selection
- Evaluating the tradeoff between performance and inference speed
Congratulations on making it this far. Throughout this book, we’ve discovered and implemented many large time models, all of which have advantages and disadvantages. We’ve experimented with these models’ zero-shot forecasting capabilities and fine-tuned them to specific scenarios.
Now we’ll cement our learning with this capstone project. The goal of this chapter is to apply what we’ve learned throughout the book in a new scenario, using a new dataset. Although a suggested solution is provided, the main idea is for you to experiment with different approaches, design experiments, and adjust each model to try to generate the most accurate forecasts possible.