Abstract: System and techniques for activity sensing online preference assay are described herein. An initial indication of an online activity preference for a member of a social network service may be obtained. A plurality of member activities corresponding with the online activity preference for a period of time subsequent to obtaining the initial indication may be collected. Respective decision trees of a set of decision trees may be traversed based on a set of inputs comprising the collected plurality of member activities to determine a probability that the online activity preference corresponds with the member. An actual online activity preference may be derived for the member using an aggregation of the determined probability for the respective decision trees of the set of decision trees. Social network content items may be filtered for the member based on the actual online activity preference.

Abstract: System and techniques for activity sensing online preference assay are described herein. A count for an action completed by a member of a social network service may be detected over a first period of time. The member may be labeled with an online activity preference based on the count and a subset of the first period of time. A plurality of member activities corresponding with the online activity preference may be collected for a second period of time prior to obtaining the initial indication. Respective decision trees of a set of decision trees may be traversed based on a set of inputs comprising the collected plurality of member activities to determine a probability that the online activity preference corresponds with the member. An actual online activity preference may be derived for the member using an aggregation of the determined probability for the respective decision trees of the set of decision trees.

Abstract: System and techniques for activity sensing online preference assay are described herein. An initial indication of an online activity preference for a member of a social network service may be obtained. A plurality of member activities corresponding with the online activity preference for a period of time subsequent to obtaining the initial indication may be collected. Respective decision trees of a set of decision trees may be traversed based on a set of inputs comprising the collected plurality of member activities to determine a probability that the online activity preference corresponds with the member. An actual online activity preference may be derived for the member using an aggregation of the determined probability for the respective decision trees of the set of decision trees.