Chapter 7: Improving and Scaling Your Forecast Strategy
To get the most out of Amazon Forecast, you can partner with your favorite data engineer or data scientist to help you improve your predictor accuracy and go further in the results postprocessing. This chapter will point you in the right direction to monitor your models and compare the predictions to real-life data; this is crucial to detect any drift in performance that would invite you to trigger retraining. Last but not least, you will also use a sample from the AWS Solutions Library to automate all your predictor training, forecast generation, and dashboard visualizations.
In this chapter, we're going to cover the following main topics:
- Deep diving into forecasting model metrics
- Understanding your model accuracy
- Model monitoring and drift detection
- Serverless architecture orchestration