Traffic flow classification using machine learning

A method comprising:

• receiving, by a communication device, data traffic;
• evaluating, by the communication device, the data traffic using an anomaly detector comprising a machine learning model trained to predict whether data traffic patterns differ from a set of observed traffic patterns present in a set of training data;
• using, by the communication device, a traffic classifier comprising a machine learning model to predict a quality of service (QoS) class for network connections or data flows for traffic that the anomaly detector predicts to be similar to the observed traffic patterns;
• and
• storing, by the communication device, data traffic that the anomaly detector predicts to be different from the observed traffic patterns.

One or more non-transitory machine-readable media storing instructions that, when executed by one or more processors of a communication device, cause the communication device to perform operations comprising:

• receiving data traffic;
• evaluating the data traffic using an anomaly detector comprising a machine learning model trained to predict whether data traffic patterns differ from a set of observed traffic patterns present in a set of training data;
• using a traffic classifier comprising a machine learning model to predict a quality of service (QoS) class for network connections or data flows for traffic that the anomaly detector predicts to be similar to the observed traffic patterns;
• and
• storing data traffic that the anomaly detector predicts to be different from the observed traffic patterns.