Chapter 14: Creating and Activating a Detector
In the previous chapter, we identified the type of anomaly detection problems that are of interest when dealing with business or operational metrics structured as univariate time series. In this chapter, we are taking a dive into using Amazon Lookout for Metrics with an e-commerce dataset that contains the evolution of the number of views and revenues over the course of a year. This dataset is hosted publicly by Amazon Web Services on the Amazon Lookout for Metrics public sample repository:
By the end of this chapter, you will have a good understanding of this dataset and you will know how to ingest it into Amazon Lookout for Metrics and use it for both backtesting and live detection purposes.
In this chapter, we're going to cover the following main topics:
- Preparing a dataset for anomaly detection purposes...