Methods and systems for assessing the quality of an item listing

Abstract

Methods and systems for enhancing a user interface of a client device are described. In an example embodiment, a machine processes a query to identify one or more item listings that satisfy the query. Each item listing is associated with at least one item being offered for sale. The machine assigns one or more scores to one or more item listings that satisfy the query based on an observed demand metric derived from historical performance data of the one or more item listings. The machine causes a presentation of the one or more item listings that satisfy the query in a search results page displayed in the user interface of the client device. The one or more item listings are positioned in the search results page based on the one or more scores assigned to the one or more item listings.

1 . (canceled) 
     
     
         2 . A computer-implemented method comprising:
 enhancing a user interface of a client device, the enhancing of the user interface including incorporating one or more modules into one or more memories of a system, the one or more modules configuring one or more hardware processors of the system to perform operations comprising:   processing a query to identify one or more item listings that satisfy the query, each item listing being associated with at least one item being offered for sale;   assigning one or more scores to one or more item listings that satisfy the query based on an observed demand metric derived from historical performance data of the one or more item listings; and   causing a presentation of the one or more item listings that satisfy the query in a search results page displayed in the user interface of the client device, the one or more item listings being positioned in the search results page based on the one or more scores assigned to the one or more item listings.   
     
     
         3 . The computer-implemented method of  claim 2 , wherein the operations further comprise:
 generating adjusted scores for the one or more item listings based on adjusting the one or more scores of the one or more item listings using an adjustment factor representing a percentage value of change,   wherein a positioning of the one or more item listings in the search results page is made based on the adjusted scores of the one or more item listings.   
     
     
         4 . The computer-implemented method of  claim 2 , wherein the historical performance data is obtained over the life of the item listing. 
     
     
         5 . The computer-implemented method of  claim 2 , wherein the historical performance data corresponds to user activity pertaining to the one or more item listings that is tracked by a machine of a server system. 
     
     
         6 . The computer-implemented method of  claim 2 , wherein the score is an observed score, and wherein the operations further comprise:
 assigning a listing quality score to the one or more item listings that satisfy the query, the listing quality score being derived as a sum of a first weighted part and a second weighted part, the first weighted part representing a first product between a first weight and a predicted score based on item attributes of a particular item listing known at listing time, and the second weighted part representing a second product between a second weight and the observed score.   
     
     
         7 . The computer-implemented method of  claim 6 , wherein the first weight and the second weight are generated based on a time-based metric. 
     
     
         8 . The computer-implemented method of  claim 6 , wherein the predicted score is further based on comparing the item attributes of the particular item listing with item attributes of other similar item listings. 
     
     
         9 . The computer-implemented method of  claim 6 , wherein the predicted score is further based on a measure of central tendency associated with prices of similar items. 
     
     
         10 . A system comprising:
 one or more hardware processors;   one or more memories of the system; and   one or more modules incorporated into the one or more memories of the system, to enhance a user interface of a client device, the enhancing including configuring the one or more hardware processors to perform operations comprising:
 processing a query to identify one or more item listings that satisfy the query, each item listing being associated with at least one item being offered for sale; 
 assigning one or more scores to one or more item listings that satisfy the query based on an observed demand metric derived from historical performance data of the one or more item listings; and 
 causing a presentation of the one or more item listings that satisfy the query in a search results page displayed in the user interface of the client device, the one or more item listings being positioned in the search results page based on the one or more scores assigned to the one or more item listings. 
   
     
     
         11 . The system of  claim 10 , wherein the operations further comprise:
 generating adjusted scores for the one or more item listings based on adjusting the one or more scores of the one or more item listings using an adjustment factor representing a percentage value of change,   wherein a positioning of the one or more item listings in the search results page is made based on the adjusted scores of the one or more item listings.   
     
     
         12 . The system of  claim 10 , wherein the historical performance data is obtained over the life of the item listing. 
     
     
         13 . The system of  claim 10 , wherein the historical performance data corresponds to user activity pertaining to the one or more item listings that is tracked by a machine of a server system. 
     
     
         14 . The system of  claim 10 , wherein the score is an observed score, and wherein the operations further comprise:
 assigning a listing quality score to the one or more item listings that satisfy the query, the listing quality score being derived as a sum of a first weighted part and a second weighted part, the first weighted part representing a first product between a first weight and a predicted score based on item attributes of a particular item listing known at listing time, and the second weighted part representing a second product between a second weight and the observed score.   
     
     
         15 . The system of  claim 14 , wherein the first weight and the second weight are generated based on a time-based metric. 
     
     
         16 . The system of  claim 14 , wherein the predicted score is further based on comparing the item attributes of the particular item listing with item attributes of other similar item listings. 
     
     
         17 . The system of  claim 14 , wherein the predicted score is further based on a measure of central tendency associated with prices of similar items. 
     
     
         18 . A non-transitory computer-readable medium storing a set of instructions that, when incorporated into a system a one or more modules implemented by one or more hardware processors, cause the one or more hardware processors to perform operations to enhance a user interface of a client device, the operations comprising:
 processing a query to identify one or more item listings that satisfy the query, each item listing being associated with at least one item being offered for sale;   assigning one or more scores to one or more item listings that satisfy the query based on an observed demand metric derived from historical performance data of the one or more item listings; and   causing a presentation of the one or more item listings that satisfy the query in a search results page displayed in the user interface of the client device, the one or more item listings being positioned in the search results page based on the one or more scores assigned to the one or more item listings.   
     
     
         19 . The non-transitory computer-readable medium of  claim 18 , wherein the operations further comprise:
 generating adjusted scores for the one or more item listings based on adjusting the one or more scores of the one or more item listings using an adjustment factor representing a percentage value of change,   wherein a positioning of the one or more item listings in the search results page is made based on the adjusted scores of the one or more item listings.   
     
     
         20 . The non-transitory computer-readable medium of  claim 18 , wherein the score is an observed score, and wherein the operations further comprise:
 assigning a listing quality score to the one or more item listings that satisfy the query, the listing quality score being derived as a sum of a first weighted part and a second weighted part, the first weighted part representing a first product between a first weight and a predicted score based on item attributes of a particular item listing known at listing time, and the second weighted part representing a second product between a second weight and the observed score.   
     
     
         21 . The non-transitory computer-readable medium of  claim 20 , wherein the predicted score is further based on comparing the item attributes of the particular item listing with item attributes of other similar item listings.