User interface for selecting sources for an online concierge system with a quick-add option for an item-source pair

1 . A method, performed at a computer system comprising a processor and a computer-readable medium, comprising:

receiving, from a client device associated with a user of an online concierge system, a request to access a user interface comprising a listing of one or more sources associated with the online concierge system, wherein each source of the one or more sources is associated with a different source location and a catalog of items;

retrieving a set of user data for the user, wherein the set of user data comprises information describing a set of interactions by the user with one or more items available at the one or more sources;

accessing a machine-learning model trained to predict a user engagement score for an item-source pair, wherein the user engagement score indicates a likelihood of an interaction by the user with an item available at a source and the machine-learning model is trained by:

receiving item data for a plurality of items available at a plurality of sources,

receiving user data for a plurality of users of the online concierge system,

receiving, for each item of the plurality of items available at each source of the plurality of sources, a label describing the interaction by one or more users with a corresponding item available at a corresponding source, and

training the machine-learning model based at least in part on the item data, the user data, and the label for each item available at each source;

applying the machine-learning model to predict the user engagement score for each item-source pair associated with the one or more sources based at least in part on the set of user data for the user;

selecting a set of item-source pairs based at least in part on the user engagement score for each item-source pair associated with the one or more sources;

generating the user interface comprising the listing of the one or more sources associated with the online concierge system and a selectable option to add, to a shopping list, an item associated with at least two item-source pairs of the selected set of item-source pairs, wherein the at least two item-source pairs are associated with different sources; and

sending the user interface to the client device associated with the user, wherein sending the user interface causes the client device to display the user interface.

2 . The method of claim 1 , further comprising:

responsive to receiving a request to select the selectable option to add an item associated with an item-source pair to the shopping list, updating the user interface to include a plurality of items included in the catalog of items associated with a corresponding item-source pair.

3 . The method of claim 1 , further comprising:

responsive to receiving a request to select the selectable option to add an item associated with an item-source pair to the shopping list, updating the shopping list to include the item associated with an item-source pair.

4 . The method of claim 1 , wherein the user engagement score for the item-source pair is specific to one or more of a quantity or an amount of the item available at the source.

5 . The method of claim 1 , wherein retrieving the set of user data for the user comprises retrieving information describing one or more of: a set of interactions by the user with a third-party website from which the user accessed the online concierge system, a set of interactions by the user with content from which the user accessed the online concierge system, a set of interactions by the user with one or more items during a previous shopping session, a set of previous conversions by the user, a time at which the user added an item to a shopping list, a shelf life associated with a previous conversion by the user, a geographical location associated with the user, one or more attributes of an item with which the user previously interacted, one or more attributes of an item associated with a previous conversion by the user, or a current time associated with the user.

6 . The method of claim 5 , wherein retrieving information describing a set of interactions by the user with content from which the user accessed the online concierge system comprises retrieving information describing a set of interactions by the user with one or more of: an email, a push notification, a content item, or a video.

7 . The method of claim 5 , wherein retrieving information describing a set of previous conversions by the user comprises retrieving one or more of: information describing a set of items associated with each conversion of the set of previous conversions, information describing a frequency of a conversion associated with an item by the user, information describing a time of each conversion of the set of previous conversions, or information describing a source associated with each conversion of the set of previous conversions.

8 . The method of claim 1 , further comprising:

retrieving a set of item data associated with each item-source pair associated with the one or more sources, wherein the set of item data comprises one or more of: information describing an availability of an item associated with each item-source pair or information describing a freshness of an item associated with each item-source pair.

9 . The method of claim 8 , wherein applying the machine-learning model to predict the user engagement score for each item-source pair associated with the one or more sources based at least in part on the set of user data for the user comprises applying the machine-learning model to predict the user engagement score for each item-source pair associated with the one or more sources based on the set of item data associated with each item-source pair associated with the one or more sources.

10 . The method of claim 1 , wherein selecting the set of item-source pairs based at least in part on the user engagement score for each item-source pair associated with the one or more sources comprises selecting the set of item-source pairs based on a number of sources included in the listing of the one or more sources associated with the online concierge system.

11 . A computer program product comprising a non-transitory computer-readable storage medium having instructions encoded thereon that, when executed by a processor, cause the processor to perform steps comprising:

receiving, from a client device associated with a user of an online concierge system, a request to access a user interface comprising a listing of one or more sources associated with the online concierge system, wherein each source of the one or more sources is associated with a different source location and a catalog of items;

retrieving a set of user data for the user, wherein the set of user data comprises information describing a set of interactions by the user with one or more items available at the one or more sources;

accessing a machine-learning model trained to predict a user engagement score for an item-source pair, wherein the user engagement score indicates a likelihood of an interaction by the user with an item available at a source and the machine-learning model is trained by:

receiving item data for a plurality of items available at a plurality of sources,

receiving user data for a plurality of users of the online concierge system,

receiving, for each item of the plurality of items available at each source of the plurality of sources, a label describing the interaction by one or more users with a corresponding item available at a corresponding source, and

training the machine-learning model based at least in part on the item data, the user data, and the label for each item available at each source;

applying the machine-learning model to predict the user engagement score for each item-source pair associated with the one or more sources based at least in part on the set of user data for the user;

selecting a set of item-source pairs based at least in part on the user engagement score for each item-source pair associated with the one or more sources;

generating the user interface comprising the listing of the one or more sources associated with the online concierge system and a selectable option to add, to a shopping list, an item associated with at least two item-source pairs of the selected set of item-source pairs, wherein the at least two item-source pairs are associated with different sources; and

sending the user interface to the client device associated with the user, wherein sending the user interface causes the client device to display the user interface.

12 . The computer program product of claim 11 , wherein the computer-readable storage medium further has instructions encoded thereon that, when executed by the processor, cause the processor to perform steps comprising:

responsive to receiving a request to select the selectable option to add an item associated with an item-source pair to the shopping list, updating the user interface to include a plurality of items included in the catalog of items associated with a corresponding item-source pair.

13 . The computer program product of claim 11 , wherein the computer-readable storage medium further has instructions encoded thereon that, when executed by the processor, cause the processor to perform steps comprising:

responsive to receiving a request to select the selectable option to add an item associated with an item-source pair to the shopping list, updating the shopping list to include the item associated with an item-source pair.

14 . The computer program product of claim 11 , wherein the user engagement score for the item-source pair is specific to one or more of a quantity or an amount of the item available at the source.

15 . The computer program product of claim 11 , wherein retrieving the set of user data for the user comprises retrieving information describing one or more of: a set of interactions by the user with a third-party website from which the user accessed the online concierge system, a set of interactions by the user with content from which the user accessed the online concierge system, a set of interactions by the user with one or more items during a previous shopping session, a set of previous conversions by the user, a time at which the user added an item to a shopping list, a shelf life associated with a previous conversion by the user, a geographical location associated with the user, one or more attributes of an item with which the user previously interacted, one or more attributes of an item associated with a previous conversion by the user, or a current time associated with the user.

16 . The computer program product of claim 15 , wherein retrieving information describing a set of interactions by the user with content from which the user accessed the online concierge system comprises retrieving information describing a set of interactions by the user with one or more of: an email, a push notification, a content item, or a video.

17 . The computer program product of claim 15 , wherein retrieving information describing a set of previous conversions by the user comprises retrieving one or more of: information describing a set of items associated with each conversion of the set of previous conversions, information describing a frequency of a conversion associated with an item by the user, information describing a time of each conversion of the set of previous conversions, or information describing a source associated with each conversion of the set of previous conversions.

18 . The computer program product of claim 11 , wherein the computer-readable storage medium further has instructions encoded thereon that, when executed by the processor, cause the processor to perform steps comprising:

retrieving a set of item data associated with each item-source pair associated with the one or more sources, wherein the set of item data comprises one or more of: information describing an availability of an item associated with each item-source pair or information describing a freshness of an item associated with each item-source pair.

19 . The computer program product of claim 18 , wherein applying the machine-learning model to predict the user engagement score for each item-source pair associated with the one or more sources based at least in part on the set of user data for the user comprises applying the machine-learning model to predict the user engagement score for each item-source pair associated with the one or more sources based on the set of item data associated with each item-source pair associated with the one or more sources.

20 . A computer system comprising:

a processor; and

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

receiving, from a client device associated with a user of an online concierge system, a request to access a user interface comprising a listing of one or more sources associated with the online concierge system, wherein each source of the one or more sources is associated with a different source location and a catalog of items;

retrieving a set of user data for the user, wherein the set of user data comprises information describing a set of interactions by the user with one or more items available at the one or more sources;

accessing a machine-learning model trained to predict a user engagement score for an item-source pair, wherein the user engagement score indicates a likelihood of an interaction by the user with an item available at a source and the machine-learning model is trained by:

receiving item data for a plurality of items available at a plurality of sources,

receiving user data for a plurality of users of the online concierge system,

receiving, for each item of the plurality of items available at each source of the plurality of sources, a label describing the interaction by one or more users with a corresponding item available at a corresponding source, and

training the machine-learning model based at least in part on the item data, the user data, and the label for each item available at each source;

applying the machine-learning model to predict the user engagement score for each item-source pair associated with the one or more sources based at least in part on the set of user data for the user;

selecting a set of item-source pairs based at least in part on the user engagement score for each item-source pair associated with the one or more sources;

generating the user interface comprising the listing of the one or more sources associated with the online concierge system and a selectable option to add, to a shopping list, an item associated with at least two item-source pairs of the selected set of item-source pairs, wherein the at least two item-source pairs are associated with different sources; and

sending the user interface to the client device associated with the user, wherein sending the user interface causes the client device to display the user interface.