Systems and techniques for ranking items

Abstract

A method for ranking items may include determining a purchaseability score for each item of a specified type based on a number of impressions of the respective item provided to users during a time period, a quantity of the respective item purchased by the users, and a quantity of the respective item added to shopping carts of the users, The method may further include ranking the items based on the purchaseability scores, generating item feed data indicating an ordering of the items based on the rankings, and providing the item feed data to a user device. The user's device may display a scrollable feed of item panels corresponding to the items, with the item panels ordered according to the ordering of the corresponding items.

1 . A computer-implemented method comprising:
 obtaining one or more user-provided ratings for an item, wherein the one or more userprovided ratings are provided by users of a computer system;   determining whether the number of user-provided ratings for the item exceeds a threshold number of ratings for the item; and   based on a determination that the number of user-provided ratings for the item does not exceed the threshold number of ratings: obtaining a plurality of predicted ratings for the item, and providing a set of ratings for the item to a device of a user, wherein the set of ratings for the item includes the one or more user-provided ratings and the plurality of predicted ratings.   
     
     
         2 . The method of  claim 1 , wherein a distribution of the predicted ratings for the item substantially matches a predicted distribution of ratings for the item. 
     
     
         3 . The method of  claim 2 , further comprising determining the predicted distribution of ratings for the item based, at least in part, on a categorization of the item, a manufacturer of the item, a seller of the item, and/or a price of the item. 
     
     
         4 . The method of  claim 2 , further comprising determining the predicted distribution of ratings for the item based, at least in part, on actual distributions of ratings for one or more other items, 
     
     
         5 . The method of  claim 4 , wherein the item and the one or more other items are in the same category or collection of items, are manufactured by the same manufacturer, are sold by the same seller, and/or have prices in the same range of prices. 
     
     
         6 . The method of  claim 1 , wherein the one or more user-provided ratings are one or more first user-provided ratings, and wherein the method further comprises:
 obtaining one or more second user-provider ratings for the item;   determining whether a combined number of the first and second user-provided ratings for the item exceeds the threshold number of ratings for the item; and   based on a determination that the combined number of user-provided ratings for the item exceeds the threshold number of ratings: providing a set of ratings for the item to a device of a user, wherein the set of ratings for the item consists of the one or more first user-provided ratings and the one or more second user-provided ratings.   
     
     
         7 . A system comprising:
 one or more computers programmed to perform operations comprising:   obtaining one or more user-provided ratings for an item, wherein the one or more user provided ratings are provided by users of a computer system;   determining whether the number of user-provided ratings for the item exceeds a threshold number of ratings for the item; and   based on a determination that the number of user-provided ratings for the item does not exceed the threshold number of ratings: obtaining a plurality of predicted ratings for the item, and providing a set of ratings for the item to a device of a user, wherein the set of ratings for the item includes the one or more user-provided ratings and the plurality of predicted ratings.   
     
     
         8 . The system of  claim 7 , wherein a distribution of the predicted ratings for the item substantially matches a predicted distribution of ratings for the item. 
     
     
         9 . The system of  claim 8 , wherein the operations further comprise determining the predicted distribution of ratings for the item based, at least in part, on a categorization of the item, a manufacturer of the item, a seller of the item, and/or a price of the item. 
     
     
         10 . The system of  claim 8 , wherein the operations further comprise determining the predicted distribution of ratings for the item based, at least in part, on actual distributions of ratings for one or more other items. 
     
     
         11 . The system of  claim 10 , wherein the item and the one or more other items are in the same category or collection of items, are manufactured by the same manufacturer, are sold by the same seller, and/or have prices in the same range of prices. 
     
     
         12 . The system of  claim 7 , wherein the one or more user-provided ratings are one or more first user-provided ratings, and wherein the operations further comprise:
 obtaining one or more second user-provider ratings for the item;   determining whether a combined number of the first and second user-provided ratings for the item exceeds the threshold number of ratings for the item; and   based on a determination that the combined number of user-provided ratings for the item exceeds the threshold number of ratings: providing a set of ratings for the item to a device of a user, wherein the set of ratings for the item consists of the one or more first user-provided ratings and the one or more second user-provided ratings.   
     
     
         13 . A computer storage medium having instructions stored thereon that, when executed by a data processing apparatus, cause the data processing apparatus to perform operations comprising:
 obtaining one or more user-provided ratings for an item, wherein the one or more user provided ratings are provided by users of a computer system;   determining whether the number of user-provided ratings for the item exceeds a threshold number of ratings for the item; and   based on a determination that the number of user-provided ratings for the item does not exceed the threshold number of ratings: obtaining a plurality of predicted ratings for the item, and providing a set of ratings for the item to a device of a user, wherein the set of ratings for the item includes the one or more user-provided ratings and the plurality of predicted ratings.   
     
     
         14 . The computer storage medium of  claim 13 , wherein a distribution of the predicted ratings for the item substantially matches a predicted distribution of ratings for the item. 
     
     
         15 . The computer storage medium of  claim 14 , wherein the operations further comprise determining the predicted distribution of ratings for the item based, at least in part, on a categorization of the item, a manufacturer of the item, a seller of the item, and/or a price of the item. 
     
     
         16 . The computer storage medium of  claim 14 , wherein the operations further comprise determining the predicted distribution of ratings for the item based, at least in part, on actual distributions of ratings for one or more other items. 
     
     
         17 . The computer storage medium of  claim 16 , wherein the item and the one or more other items are in the same category or collection of items, are manufactured by the same manufacturer, are sold by the same seller, and/or have prices in the same range of prices. 
     
     
         18 . The computer storage medium of  claim 13 , wherein the one or more user-provided ratings are one or more first user-provided ratings, and wherein the operations further comprise:
 obtaining one or more second user-provider ratings for the item;   determining whether a combined number of the first and second user-provided ratings for the item exceeds the threshold number of ratings for the item; and   based on a determination that the combined number of user-provided ratings for the item exceeds the threshold number of ratings: providing a set of ratings for the item to a device of a user, wherein the set of ratings for the item consists of the one or more first user-provided ratings and the one or more second user-provided ratings.