Method and system for electronic advertising

A method of providing publishers real time predictions of whether users will complete transactions in user interfaces of the publishers, the method comprising:

• using a processor to perform:
• receiving, through a communication network from the user interface, information about a particular user interacting with a user interface associated with a publisher system, the information about the particular user including information obtained based on activity of the particular user in the user interface associated with the publisher system;
• accessing, from memory, a model of user behavior in the user interface associated with the publisher system;
• determining an indication of predicted likelihood that the particular user will perform the transaction in the user interface associated with the publisher system, the determining comprising segmenting, using the model and the information about the particular user, the particular user into one of a plurality of groups, the plurality of groups indicating different predicted likelihoods that a given user will complete the transaction in the user interface associated with the publisher system;
• and
• transmitting, through the communication network to the user interface, the indication of predicted likelihood that the particular user will perform the transaction in the user interface associated with the publisher system.

A non-transitory computer-readable storage medium storing instructions that, when executed by a processor, cause the processor to perform a method comprising:

• receiving, through a communication network from the user interface, information about a particular user interacting with a user interface associated with a publisher system, the information about the particular user including information obtained based on activity of the particular user in the user interface associated with the publisher system;
• accessing, from memory, a model of user behavior in the user interface associated with the publisher system;
• determining an indication of predicted likelihood that the particular user will perform the transaction in the user interface associated with the publisher system, the determining comprising segmenting, using the model and the information about the particular user, the particular user into one of a plurality of groups, the plurality of groups indicating different predicted likelihoods that a given user will complete the transaction in the user interface associated with the publisher system;
• and
• transmitting, through the communication network to the user interface, the indication of predicted likelihood that the particular user will perform the transaction in the user interface associated with the publisher system.