Abstract: Techniques for onboarding users to various product features are described. According to various embodiments, information identifying a set of candidate onboarding content items associated with an email type of an email to be transmitted to a particular member of an online social network service is accessed. Thereafter, a first subset of the candidate onboarding content items is removed from the set, responsive to determining that the particular member has already been onboarded to products associated with the candidate onboarding content items in the first subset. Further, a second subset of the candidate onboarding content items is removed from the set, responsive to determining that the particular member has previously viewed and not interacted with the candidate onboarding content items in the second subset. A specific onboarding content item is then dynamically selected from the remaining set of candidate onboarding content items.

Abstract: Techniques for onboarding users to online product features are described. According to various embodiments, email content data describing an email type of an email to be transmitted to a particular member is accessed. Information identifying a plurality of candidate onboarding content items associated with the email type is also accessed. Feature data including member onboarding content item interaction data describing the particular member's interactions with various onboarding content items is also accessed. Thereafter, for the particular member and the email type, a relevance score is generated for each of the candidate onboarding content items, based on the email content data and the member onboarding content item interaction data. Each of the relevance scores may indicate a likelihood that the particular member selects the corresponding candidate onboarding content item.

Abstract: Techniques for onboarding users to online product features are described. According to various embodiments, email content data describing an email type of an email to be transmitted to a particular member is accessed. Information identifying a plurality of candidate onboarding content items associated with the email type is also accessed. Feature data including member onboarding content item interaction data describing the particular member's interactions with various onboarding content items is also accessed. Thereafter, for the particular member and the email type, a relevance score is generated for each of the candidate onboarding content items, based on the email content data and the member onboarding content item interaction data. Each of the relevance scores may indicate a likelihood that the particular member selects the corresponding candidate onboarding content item.

Abstract: Techniques for onboarding users to various product features are described. According to various embodiments, information identifying a set of candidate onboarding content items associated with an email type of an email to be transmitted to a particular member of an online social network service is accessed. Thereafter, a first subset of the candidate onboarding content items is removed from the set, responsive to determining that the particular member has already been onboarded to products associated with the candidate onboarding content items in the first subset. Further, a second subset of the candidate onboarding content items is removed from the set, responsive to determining that the particular member has previously viewed and not interacted with the candidate onboard* content items in the second subset. A specific onboarding content item is then dynamically selected from the remaining set of candidate onboarding content items.