Abstract: Some implementations allow users to create and share data including playlists. Such playlists may be subscribed to by other users. Changes to such playlists, such as updates by the curator of the playlist, must be propagated to subscribers in a timely manner while efficiently utilizing resources. Some implementations allow updates to be propagated using a push notification to cause client devices to request the update (push). Alternatively, updates may be made when the client devices of the subscribers next accesses the system (pull). An aggregator system may be used to make decisions on which users to send push notifications, and which users to wait to pull updates on their own. Additionally, the aggregator may determine that certain playlist updates should be distributed using push notifications. The aggregator may determine that only certain playlist subscribers should receive push notifications regarding playlist updates.

Abstract: Methods and systems are provided to identify and present filters. The system receives a query, over a network, from a client machine and identifies a filter context based on the query. The filter context including a first plurality of filters. The system further identifies a second plurality of filters responsive the receiving the query. The identifying the second plurality of filters is based on the filter context and a plurality of probabilities. The system generates a user interface including search results that are identified based on the filter context. The system communicates the user interface, over the network, to the client machine.

Abstract: In some implementations, a computing device can improve diversity in media item recommendations. For example, the computing device can generate a satisfaction score representing an estimate of the amount satisfaction a user will experience when a candidate media item selected by the user is presented (e.g., played) by the system. The system can determine the difference in satisfaction scores for similar media items over time to determine the amount of satisfaction gained with a subsequent selection and presentation of similar candidate media items. The system can rank candidate media items based the satisfaction gain calculated for each candidate media item and select suggested media items to present to the user based on the candidate media items having the highest satisfaction gain. In some implementations, the computing device can generate satisfaction scores based on an adventurousness score calculated for the user.

Abstract: Some implementations allow users to create and share data including playlists. Such playlists may be subscribed to by other users. Changes to such playlists, such as updates by the curator of the playlist, must be propagated to subscribers in a timely manner while efficiently utilizing resources. Some implementations allow updates to be propagated using a push notification to cause client devices to request the update (push). Alternatively, updates may be made when the client devices of the subscribers next accesses the system (pull). An aggregator system may be used to make decisions on which users to send push notifications, and which users to wait to pull updates on their own. Additionally, the aggregator may determine that certain playlist updates should be distributed using push notifications. The aggregator may determine that only certain playlist subscribers should receive push notifications regarding playlist updates.

Abstract: Some implementations allow users to create and share data including playlists. Such playlists may be subscribed to by other users. Changes to such playlists, such as updates by the curator of the playlist, must be propagated to subscribers in a timely manner while efficiently utilizing resources. Some implementations allow updates to be propagated using a push notification to cause client devices to request the update (push). Alternatively, updates may be made when the client devices of the subscribers next accesses the system (pull). An aggregator system may be used to make decisions on which users to send push notifications, and which users to wait to pull updates on their own. Additionally, the aggregator may determine that certain playlist updates should be distributed using push notifications. The aggregator may determine that only certain playlist subscribers should receive push notifications regarding playlist updates.

Abstract: In some implementations, a computing device can improve diversity in media item recommendations. For example, the computing device can generate a satisfaction score representing an estimate of the amount satisfaction a user will experience when a candidate media item selected by the user is presented (e.g., played) by the system. The system can determine the difference in satisfaction scores for similar media items over time to determine the amount of satisfaction gained with a subsequent selection and presentation of similar candidate media items. The system can rank candidate media items based the satisfaction gain calculated for each candidate media item and select suggested media items to present to the user based on the candidate media items having the highest satisfaction gain. In some implementations, the computing device can generate satisfaction scores based on an adventurousness score calculated for the user.

Abstract: Systems and methods to identify values for a selected filter are described. The system receives a selection from a client machine. The selection identifies a filter that includes a first attribute-value pair that includes a first attribute and a first value, the first attribute-value pair being included in a concept query that was extracted from a query including at least one keyword that was received over the network from the client machine. The system further identifies filters responsive to receiving the selection, the identification of the filters being based on the first attribute and probabilities describing occurrences of attribute-value pairs in listings that respectively describe items that were previously transacted on a network-based marketplace, the filters including values. The system further generates a user interface including the values and search results that are identified based on the concept query and communicate the user interface to the client machine.

Abstract: Methods and systems are provided to identify and present filters. The system receives a query, over a network, from a client machine and identifies a filter context based on the query. The filter context including a first plurality of filters. The system further identifies a second plurality of filters responsive the receiving the query. The identifying the second plurality of filters is based on the filter context and a plurality of probabilities. The system generates a user interface including search results that are identified based on the filter context. The system communicates the user interface, over the network, to the client machine.

Abstract: Systems and methods to identify and present filters are described. The system receives a query from a client machine, the query including at least one keyword. The system further identifies a filter context based on the query, the filter context including a first set of filters including attribute-value pairs, the attribute-value pairs including a first attribute-value pair including a first filter and a second attribute-value pair including a second filter. The system further identifies a second set of filters responsive to receiving the query, the identifying the second set of filters is based on the filter context and probabilities describing occurrences of attribute-value pairs in listings that respectively describe items that were previously transacted on a network-based marketplace. The system further generates a user interface including search results that are identified based on the filter context and communicates the user interface to the client machine.

Abstract: Some implementations allow users to create and share data including playlists. Such playlists may be subscribed to by other users. Changes to such playlists, such as updates by the curator of the playlist, must be propagated to subscribers in a timely manner while efficiently utilizing resources. Some implementations allow updates to be propagated using a push notification to cause client devices to request the update (push). Alternatively, updates may be made when the client devices of the subscribers next accesses the system (pull). An aggregator system may be used to make decisions on which users to send push notifications, and which users to wait to pull updates on their own. Additionally, the aggregator may determine that certain playlist updates should be distributed using push notifications. The aggregator may determine that only certain playlist subscribers should receive push notifications regarding playlist updates.

Abstract: Systems and methods to identify and present filters are described. The system receives a query from a client machine, the query including at least one keyword. The system further identifies a filter context based on the query, the filter context including a first set of filters including attribute-value pairs, the attribute-value pairs including a first attribute-value pair including a first filter and a second attribute-value pair including a second filter. The system further identifies a second set of filters responsive to receiving the query, the identifying the second set of filters is based on the filter context and probabilities describing occurrences of attribute-value pairs in listings that respectively describe items that were previously transacted on a network-based marketplace. The system further generates a user interface including search results that are identified based on the filter context and communicates the user interface to the client machine.

Abstract: Systems and methods to identify values for a selected filter are described. The system receives a selection from a client machine. The selection identifies a filter that includes a first attribute-value pair that includes a first attribute and a first value, the first attribute-value pair being included in a concept query that was extracted from a query including at least one keyword that was received over the network from the client machine. The system further identifies filters responsive to receiving the selection, the identification of the filters being based on the first attribute and probabilities describing occurrences of attribute-value pairs in listings that respectively describe items that were previously transacted on a network-based marketplace, the filters including values. The system further generates a user interface including the values and search results that are identified based on the concept query and communicate the user interface to the client machine.