Behavioral targeting system

A computing system for behavioral targeting comprising:

• at least one hardware processor;
• a storage medium for tangibly storing thereon program logic for execution by the processor, the program logic comprising:
• event receiving logic, executed by the processor, for receiving a plurality of events generated by a user;
• event classifying logic, executed by the processor, for classifying each of the plurality of received events in one of a plurality of categories;
• model selecting logic, executed by the processor, for selecting, as each of the plurality of events is received, a model from a plurality of models based on a marketing objective, the selected model comprising rules used for dimension processing;
• model applying logic, executed by the processor, for applying upon execution of the model selection logic, the rules of the selected model to user data comprising at least the plurality of received events for determining interest of the user in the plurality of categories;
• short-term raw score generating logic, executed by the processor, for generating at least a plurality of short-term raw user interest scores of the user for the plurality of categories into which the plurality of received events are classified via the application of the rules, the raw user interest scores are indicative of interest of the user in the plurality of categories into which the plurality of received events are classified;
• and
• communicating logic, executed by the processor, for communicating the short-term raw user interest scores to an advertising server for enabling serving advertisements for small purchases customized to the short-term interests of the user, the small purchases comprising purchases made in a pre-defined period of time.

A non-transitory computer readable storage medium for behavioral targeting, comprising instructions, which when executed by a processor cause the processor to:

• receive a plurality of events generated by a user;
• classify each of the plurality of received events into one of a plurality of categories;
• select, as each of the plurality of events is received, a model from a plurality of models based on a marketing objective, the selected model comprising rules used for dimension processing;
• apply, upon the selection, the rules of the selected model to user data comprising at least the plurality of received events for determining interest of the user in the plurality of categories into which the plurality of received events are classified;
• generate at least a plurality of short-term raw user interest scores of the user for the plurality of categories into which the plurality of received events are classified via the application of the rules wherein the short-term raw user interest scores are indicative of interest of the user in the plurality of categories into which the plurality of received events are classified;
• and
• communicate the short-term raw user interest scores to an advertising server for enabling serving advertisements for small purchases customized to the short term interests of the user, the small purchases comprising purchases made in a pre-defined period of time.