Calculating bids for content items based on value of a product associated with the content item

Abstract

An online system calculates bids for content items to display to users based on the value of a product described in the content item and the likelihood of a viewing user purchasing the product. The online system identifies an impression opportunity for an ad request and computes an expected value of the conversion and a likelihood of the conversion. The online system computes a bid amount based on the expected conversion value and the likelihood of the conversion. Bids based on the value of the conversion allow a third party system offering the product to optimize for the value of each conversion instead of the conversion rate.

1 .- 20 . (canceled) 
     
     
         21 . A method comprising:
 receiving, by a processor of an online system, a request from a third party system to present a content item describing a product;   identifying, by the processor, an impression opportunity to present the content item of the third party system to a particular viewing user of the online system;   determining, by the processor, an expected amount the particular viewing user will spend on converting the product in the content item given the impression opportunity;   computing, by the processor, a bid amount for presenting the content item of the third party system based on a minimum return on investment (ROI) for the third party system, a likelihood of a conversion of the content item by the particular viewing user, and the expected amount the particular viewing user will spend on converting the product in the content item; and   providing the computed bid amount for presenting the content item of the third party system to a content item selection process.   
     
     
         22 . The method of  claim 21 , wherein the computed bid amount is a product of the minimum ROI, the likelihood of the conversion of the content item by the particular viewing user, and a weight associated with the expected amount the particular viewing user will spend converting on the product in the content item. 
     
     
         23 . The method of  claim 21 , wherein determining the expected amount the particular viewing user will spend on converting the product in the content item comprises:
 obtaining, from a plurality of third party systems, spending data of a plurality of users that share one or more characteristics in common with the particular viewing user, wherein the spending data corresponds to purchases made by the plurality of users; and   training a machine learning model to determine the expected amount the particular viewing user will spend on a purchase of the product based on the spending data of the plurality of users.   
     
     
         24 . The method of  claim 23 , wherein the spending data of the plurality of users is obtained from the third party systems via tracking pixels on websites associated with the third party systems. 
     
     
         25 . The method of  claim 21 , further comprising:
 selecting, in the content item selection process, the content item of the third party system for presentation to the particular viewing user based on the computed bid amount;   providing the content item of the third party system for display to the particular viewing user;   tracking one or more interactions between the particular viewing user and the content item;   receiving an indication that a conversion associated with the content item occurred; and   attributing a portion of the expected amount the particular viewing user will spend on converting the product in the content item as an attributed spending.   
     
     
         26 . The method of  claim 21 , further comprising:
 determining, by the processor, the minimum ROI for the third party system corresponding to an amount that the third party system is willing to pay per unit of value of a conversion of the content item.   
     
     
         27 . The method of  claim 21 , further comprising:
 obtaining user profile information for the particular viewing user; and   determining, based on the user profile information, the likelihood of the conversion of the content item by the particular viewing user.   
     
     
         28 . A non-transitory computer-readable storage medium storing instructions that when executed by a processor cause the processor to:
 receive a request from a third party system to present a content item describing a product;   identify an impression opportunity to present the content item of the third party system to a particular viewing user of an online system;   determine an expected amount the particular viewing user will spend on converting the product in the content item given the impression opportunity;   compute a bid amount for presenting the content item of the third party system based on a minimum return on investment (ROI) for the third party system, a likelihood of a conversion of the content item by the particular viewing user, and the expected amount the particular viewing user will spend on converting the product in the content item; and   provide the computed bid amount for presenting the content item of the third party system to a content item selection process.   
     
     
         29 . The non-transitory computer-readable storage medium of  claim 28 , wherein the computed bid amount is a product of the minimum ROI, the likelihood of the conversion of the content item by the particular viewing user, and a weight associated with the expected amount the particular viewing user will spend converting on the product in the content item. 
     
     
         30 . The non-transitory computer-readable storage medium of  claim 28 , wherein, to determine the expected amount the particular viewing user will spend on converting the product in the content item, the instructions cause the processor to:
 obtain, from a plurality of third party systems, spending data of a plurality of users that share one or more characteristics in common with the particular viewing user, wherein the spending data corresponds to purchases made by the plurality of users; and   train a machine learning model to determine the expected amount the particular viewing user will spend on a purchase of the product based on the spending data of the plurality of users.   
     
     
         31 . The non-transitory computer-readable storage medium of  claim 30 , wherein the spending data of the plurality of users is obtained from the third party systems via tracking pixels on websites associated with the third party systems. 
     
     
         32 . The non-transitory computer-readable storage medium of  claim 28 , wherein the instructions further cause the processor to:
 select, in the content item selection process, the content item of the third party system for presentation to the particular viewing user based on the computed bid amount;   provide the content item of the third party system for display to the particular viewing user;   track one or more interactions between the particular viewing user and the content item;   receive an indication that a conversion associated with the content item occurred; and   attribute a portion of the expected amount the particular viewing user will spend on converting the product in the content item as an attributed spending.   
     
     
         33 . The non-transitory computer-readable storage medium of  claim 28 , wherein the instructions further cause the processor to:
 determine the minimum ROI for the third party system corresponding to an amount that the third party system is willing to pay per unit of value of a conversion of the content item.   
     
     
         34 . The non-transitory computer-readable storage medium of  claim 28 , wherein the instructions further cause the processor to:
 obtain user profile information for the particular viewing user; and   determine, based on the user profile information, the likelihood of the conversion of the content item by the particular viewing user.   
     
     
         35 . A computing device comprising:
 a processor; and   a memory storing instructions that when executed by the processor cause the processor to:
 receive a request from a third party system to present a content item describing a product; 
 identify an impression opportunity to present the content item of the third party system to a particular viewing user of an online system; 
 determine an expected amount the particular viewing user will spend on converting the product in the content item given the impression opportunity; 
 compute a bid amount for presenting the content item of the third party system based on a minimum return on investment (ROI) for the third party system, a likelihood of a conversion of the content item by the particular viewing user, and the expected amount the particular viewing user will spend on converting the product in the content item; and 
 provide the computed bid amount for presenting the content item of the third party system to a content item selection process. 
   
     
     
         36 . The computing device of  claim 35 , wherein the computed bid amount is a product of the minimum ROI, the likelihood of the conversion of the content item by the particular viewing user, and a weight associated with the expected amount the particular viewing user will spend converting on the product in the content item. 
     
     
         37 . The computing device of  claim 35 , wherein, to determine the expected amount the particular viewing user will spend on converting the product in the content item, the instructions cause the processor to:
 obtain, from a plurality of third party systems, spending data of a plurality of users that share one or more characteristics in common with the particular viewing user, wherein the spending data corresponds to purchases made by the plurality of users; and   train a machine learning model to determine the expected amount the particular viewing user will spend on a purchase of the product based on the spending data of the plurality of users.   
     
     
         38 . The computing device of  claim 35 , wherein the instructions further cause the processor to:
 select, in the content item selection process, the content item of the third party system for presentation to the particular viewing user based on the computed bid amount;   provide the content item of the third party system for display to the particular viewing user;   track one or more interactions between the particular viewing user and the content item;   receive an indication that a conversion associated with the content item occurred; and   attribute a portion of the expected amount the particular viewing user will spend on converting the product in the content item as an attributed spending.   
     
     
         39 . The computing device of  claim 35 , wherein the instructions further cause the processor to:
 determine the minimum ROI for the third party system corresponding to an amount that the third party system is willing to pay per unit of value of a conversion of the content item.   
     
     
         40 . The computing device of  claim 35 , wherein the instructions further cause the processor to:
 obtain user profile information for the particular viewing user; and   determine, based on the user profile information, the likelihood of the conversion of the content item by the particular viewing user.