Viewpoint data logging for improved feed relevance

A non-transitory computer readable medium comprising instructions which, when implemented by a processor, cause the processor to perform operations comprising:

• receive a request to generate a feed for an online social networking system, the feed to be displayed on a user interface associated with a member of the online social networking system;
• obtain from an activity database of the online social networking system, activity data of content items of the online social networking system, the activity data including:
• duration data indicative of a duration in which at least some of the content items has previously been displayed on other feeds of members of the online social networking system, the duration data provided, at least in part, to the activity database by client devices on which the feeds were displayed, wherein the duration data comprises a first time at which a first percentage of associated content item was displayed on a prior feed and a second time at which a second percentage of the associated content item was no longer displayed on the prior feed;
• and
• interactions with the content items by the members;
• for each of the content items, determine a probability score of the member to interact with the content item by applying a logistic regression model to the duration data and the interactions to determine, at least in part, a probability score of the member to interact with the content item;
• generate the feed with at least some of the content items having an order based on the probability score for each of the at least some content items;
• and
• transmit, via a network interface, the feed as generated to a client device associated with the member.

A system, comprising:

• a non-transitory computer readable medium comprising instructions which, when implemented by a processor, cause the processor to perform operations comprising:
• receive a request to generate a feed for an online social networking system, the feed to be displayed on a user interface associated with a member of the online social networking system;
• obtain from an activity database of the online social networking system, activity data of content items of the online social networking system, the activity data including:
• duration data indicative of a duration in which at least some of the content items has previously been displayed on other feeds of members of the online social networking system, the duration data provided, at least in part, to the activity database by client devices on which the feeds were displayed, wherein the duration data comprises a first time at which a first percentage of associated content item was displayed on a prior feed and a second time at which a second percentage of the associated content item was no longer displayed on the prior feed;
• and
• interactions with the content items by the members;
• for each of the content items, determine a probability score of the member to interact with the content item by applying a logistic regression model to the duration data and the interactions to determine, at least in part, a probability score of the member to interact with the content item;
• generate the feed with at least some of the content items having an order based on he probability score for each of the at least some content items;
• and
• transmit, via a network interface, the feed as generated to a client device associated with the member.