A targeted advertising system uses a machine learning tool to select an assetfor a current user of a user equipment device, for example, to select an ad for deliveryto a current user (1302) of a digital set top box (1304) in a cable network. The machinelearning tool first operates in a learning mode to receive user inputs (1310)and develop evidence that can characterize multiple users of the user equipmentdevice audience. In a working mode, the machine learning tool processes currentuser inputs to match a current user (1302) to one of the identified users of thatuser equipment device audience. Fuzzy logic may be used to improve developmentof the user characterizations, as well as matching of the current user to thosedeveloped characterizations. In this manner, targeting of assets can be implementednot only based on characteristics of a household but based on a current user withinthat household.
展开▼