Content Item Impression Effect Decay

Abstract

When a content item is initially served to a client device, the content item may result in an impression effect. As time elapses, the initial impression may fade. Such a decay of the impression effect may be predicted through the use of a predictive model. In some implementations, one or more impression effect parameters may be accessed and used with the predictive model to determine a decay factor or predicted value that incorporates the impression effect decay for a content item. A value, such as a score, may be determined based on the decay factor or the predicted value and a bid associated with a content item. A content item may be selected based on the determined value and data to effect presentation of the content item may be provided.

1 .- 20 . (canceled) 
     
     
         21 . A system to distribute data delivery, comprising:
 a data processing system comprising one or more processors and one or more storage devices to:   identify a predictive model based on one or more impression effect parameters indicating historical engagement by a client device with a content item, wherein the predictive model reduces a likelihood that the content item is selected and served by the data processing system within a time interval subsequent to an initial impression of the content item;   determine a decay factor of the one or more impression effect parameters within the time interval subsequent to the initial impression of the content item;   modify the decay factor based on a resource with which the content item is presented;   determine, for the client device, a value for the content item based on the predictive model, wherein the predictive model is modified by the decay factor such that one or more impression effect parameters is reduced by the decay factor; and   select, based at least in part on the value, the content item with which the client device performed an interaction.   
     
     
         22 . The system of  claim 21 , comprising:
 the data processing system to generate the predictive model based at least on one or more presentation effect parameters.   
     
     
         23 . The system of  claim 21 , comprising:
 the data processing system to determine the value based at least in part on a decay factor of a presentation effect for the content item based on the predictive model.   
     
     
         24 . The system of  claim 21 , comprising:
 the data processing system to determine the value based at least in part on a bid associated with the content item, the bid provided by a third-party content provider.   
     
     
         25 . The system of  claim 21 , comprising:
 the data processing system to determine the value based on a decay factor of the predictive model and a bid value associated with the content item.   
     
     
         26 . The system of  claim 21 , comprising:
 the data processing system to determine the interaction comprises speech input.   
     
     
         27 . The system of  claim 21 , comprising:
 the data processing system to provide the content item comprising audio output to cause the client device to play the audio output to present the content item.   
     
     
         28 . The system of  claim 21 , wherein the client device comprises a digital assistant. 
     
     
         29 . The system of  claim 21 , comprising:
 the data processing system to determine the interaction comprises a conversion action.   
     
     
         30 . The system of  claim 21 , wherein the historical engagement includes one or more prior presentations of the content item associated with the client device within a prior predetermined period of time. 
     
     
         31 . A method to distribute data delivery, comprising:
 identifying a predictive model based on one or more impression effect parameters indicating historical engagement by a client device with a content item, wherein the predictive model reduces a likelihood that the content item is selected and served by the data processing system within a time interval subsequent to an initial impression of the content item;   determining a decay factor of the one or more impression effect parameters within the time interval subsequent to the initial impression of the content item;   modifying the decay factor based on a resource with which the content item is presented;   determining, for the client device, a value for the content item based on the predictive model, wherein the predictive model is modified by the decay factor such that one or more impression effect parameters is reduced by the decay factor; and   selecting, based at least in part on the value, the content item with which the client device performed an interaction.   
     
     
         32 . The method of  claim 31 , comprising:
 generating, by the data processing system, the predictive model based at least on one or more presentation effect parameters.   
     
     
         33 . The method of  claim 31 , comprising:
 determining, by the data processing system, the value based at least in part on a decay factor of a presentation effect for the content item based on the predictive model.   
     
     
         34 . The method of  claim 31 , comprising:
 determining, by the data processing system, the value based at least in part on a bid associated with the content item, the bid provided by a third-party content provider.   
     
     
         35 . The method of  claim 31 , comprising:
 determining, by the data processing system, the value based on a decay factor of the predictive model and a bid value associated with the content item.   
     
     
         36 . The method of  claim 31 , comprising:
 determining, by the data processing system, the interaction comprises speech input.   
     
     
         37 . The method of  claim 31 , comprising:
 providing, by the data processing system, the content item comprising audio output to cause the client device to play the audio output to present the content item.   
     
     
         38 . The method of  claim 31 , wherein the client device comprises a digital assistant. 
     
     
         39 . The method of  claim 31 , comprising:
 determining, by the data processing system, the interaction comprises a conversion action.   
     
     
         40 . The method of  claim 31 , wherein the historical engagement includes one or more prior presentations of the content item associated with the client device within a prior predetermined period of time.