As mentioned earlier, the application we will be creating is a network traffic anomaly detector. Given a set of attributes relating to the network traffic amount (in bytes), the application will use that data to find anomalies in the amount of traffic for a given checkpoint. As with other applications, this is not meant to power the next ML network traffic anomaly detection product; however, it will show you how to use time series in ML.NET, specifically to detect spikes with SSA.
As with previous chapters, the completed project code, sample dataset, and project files can be downloaded here: https://github.com/PacktPublishing/Hands-On-Machine-Learning-With-ML.NET/tree/master/chapter06-time-series.
Exploring the project architecture
Building on the project architecture and code we created in previous chapters, the bulk of the changes are in the training of the model as time series requires a fairly significant paradigm shift from what we have reviewed...
