Recommending content

摘要

A method for recommending content items to a user is provided. It includes: (i) receiving one of at least an acceptance input and a rejection input from a user in relation to content presented to the user; (ii) in response to an acceptance input, rendering the presented content, or in response to a rejection input, selecting fresh content for presentation; and, (iii) repeating steps (i) and (ii) until a acceptance input is received. Content is selected in dependence on a associated probability associated with that content. The probability is increased in response to an acceptance input, the increase being determined in part on a measure of a predicted reduction in user satisfaction that would be associated with an additional rejection input.

主权项

1. Method for recommending content items, comprising:
(i) receiving one of at least a first input and a second input from a user in relation to presented content; (ii) in response to a first input, rendering the presented content, or in response to a second input, increasing a count value indicative of a number of second inputs received prior to receipt of a first input and selecting fresh content for presentation; and, (iii) repeating (i) and (ii) until a first input is received, wherein content has a probability associated therewith, and content is selected in dependence on the associated probability of that content, the first and second inputs being received and the selection of the content being performed locally; and, wherein the probability associated with a given content is increased each time a first input is received from the user for that content, a magnitude of the increase being dependent on the count value for said content; and computing a measure of system performance based on the count value upon receipt of a first input.