Device identifier classification

A network device comprising a processing resource in communication with a memory resource including instructions executable to:

• continuously track a plurality of attributes associated with a plurality of unique client device identifiers received at the network device and stored in a tracking table;
• determine a statistical property of each one of the plurality of unique client device identifiers based on the plurality of attributes;
• generate a data set for an unsupervised machine learning mechanism based at least on the determined statistical properties;
• receive a label for each one of the plurality of unique client device identifiers based at least on a plurality of clusters determined by the unsupervised machine learning mechanism;
• generate a decision tree classifier for the plurality of unique client device identifiers using a decision tree machine learning mechanism and based on the received labels and the determined statistical properties;
• and
• classify a new unique device identifier received at the network device using the decision tree classifier.

A non-transitory computer-readable medium storing instructions executable by the processing resource to:

• determine a plurality of attributes and a plurality of statistical properties associated with each one of a plurality of unique client device identifiers received at a switching device;
• generate a data set based of the plurality of attributes and the plurality of statistical properties;
• cluster, into a plurality of clusters, the generated data set using an unsupervised machine learning mechanism;
• create a classifier for each of the plurality of clusters using a supervised machine learning mechanism and based on labels received by the switching device for each one of the plurality of unique client device identifiers;
• and
• dynamically classify new unique client device identifiers continuously received at the switching device using the created classifiers.