With k-means clustering models behind us, it is now time to dive into anomaly detection models. Anomaly detection is one of the newer additions to ML.NET, and specifically, time-series transforms. In this chapter, we will dive into anomaly detection and the various applications best suited to utilizing anomaly detection. In addition, we will build two new example applications: one anomaly detection application that determines whether the login attempt is abnormally demonstrating the randomized PCA trainer, and one that demonstrates time series in a network traffic anomaly detection application. Finally, we will explore how to evaluate an anomaly detection model with the properties that ML.NET exposes.
In this chapter, ...
