Generating in-channel and cross-channel promotion recommendations using promotion cross sell

Abstract

In general, embodiments of the present invention provide systems, methods and computer readable media for recommending contextually relevant promotions to consumers in order to facilitate their discovery of promotions that they are likely to purchase from a promotion and marketing service.

1 - 20 . (canceled) 
     
     
         21 . A computer-implemented method comprising:
 receiving, by a processor, promotion data describing a set of promotions;   causing, by the processor, rendering of an electronic user interface to a first consumer device associated with a first consumer, the electronic user interface comprising a plurality of impressions, wherein the plurality of impressions are respectively associated with a displayed promotion subset of the set of promotions;   receiving, by the processor, clickstream data indicating real time interaction by the first consumer with a particular impression of the plurality of impressions, wherein the particular impression is associated with a particular promotion;   generating, by the processor, a plurality of ranked sets of promotions, wherein the plurality of ranked sets of promotions comprises at least (i) a first ranked set generated based at least in part on a first ranking routine, (ii) a second ranked set generated based at least in part on a second ranking routine different from the first ranking routine, and (iii) a third ranked set generated based at least in part on a third ranking routine different from the first ranking routine and the second ranking routine, wherein the third ranking routine is based at least in part on a plurality of cross-sell signals collected using a group of cross-sell widgets;   generating, by the processor, a ranked set of related promotions for the particular promotion by merging at least the first ranked set, the second ranked set, and the third ranked set based at least in part on an arrangement merger routine; and   causing, by the processor, updating of the electronic user interface to display an updated plurality of impressions associated with the ranked set of related promotions simultaneously with and positioned proximate to the particular impression associated with the particular promotion.   
     
     
         22 . The computer-implemented method of  claim 21 , wherein the first ranking routine is related to a measure of similarity between a static attribute of the particular promotion and one or more static attributes of one or more other promotions. 
     
     
         23 . The computer-implemented method of  claim 21 , wherein the second ranking routine is related to a measure of correlation between a purchase history attribute of the particular promotion and one or more purchase history attributes of one or more other promotions. 
     
     
         24 . The computer-implemented method of  claim 23 , wherein the second ranking routine is based at least in part on one or more historical co-purchases from a first service associated with the particular promotion over a period of time. 
     
     
         25 . The computer-implemented method of  claim 24 , wherein a historical co-purchase of the one or more historical co-purchases represents a purchase, by another consumer of a plurality of consumers, of both the particular promotion and a second promotion from a second service within the period of time. 
     
     
         26 . The computer-implemented method of  claim 21 , wherein the group of cross-sell widgets comprises a user-specific recommendations widget that collects signals based on recent purchase history. 
     
     
         27 . The computer-implemented method of  claim 21 , wherein the group of cross-sell widgets comprises a views-based conversion widget that collects signals describing a portion of consumers that went on to buy the particular promotion relative to other viewed promotions. 
     
     
         28 . The computer-implemented method of  claim 21 , wherein the group of cross-sell widgets comprises a purchase-based widget that collects signals describing a portion of consumers that went on to buy the particular promotion relative to other purchased promotions. 
     
     
         29 . The computer-implemented method of  claim 21 , wherein the group of cross-sell widgets comprises a search history widget that collects signals describing the first consumer's search history. 
     
     
         30 . The computer-implemented method of  claim 21 , wherein the group of cross-sell widgets comprise a newly launched promotions widget that collects signals describing newly launched promotions relevant to the first consumer. 
     
     
         31 . An apparatus comprising at least one processor and at least one non-transitory memory comprising program code, wherein the at least one non-transitory memory and the program code are configured to, with the at least one processor, cause the apparatus to:
 receive promotion data describing a set of promotions;   cause rendering of an electronic user interface to a first consumer device associated with a first consumer, the electronic user interface comprising a plurality of impressions, wherein the plurality of impressions are respectively associated with a displayed promotion subset of the set of promotions;   receive clickstream data indicating real time interaction by the first consumer with a particular impression of the plurality of impressions, wherein the particular impression is associated with a particular promotion;   generate a plurality of ranked sets of promotions, wherein the plurality of ranked sets of promotions comprises at least (i) a first ranked set generated based at least in part on a first ranking routine, (ii) a second ranked set generated based at least in part on a second ranking routine different from the first ranking routine, and (iii) a third ranked set generated based at least in part on a third ranking routine different from the first ranking routine and the second ranking routine, wherein the third ranking routine is based at least in part on a plurality of cross-sell signals collected using a group of cross-sell widgets;   generate a ranked set of related promotions for the particular promotion by merging at least the first ranked set, the second ranked set, and the third ranked set based at least in part on an arrangement merger routine; and   cause updating of the electronic user interface to display an updated plurality of impressions associated with the ranked set of related promotions simultaneously with and positioned proximate to the particular impression associated with the particular promotion.   
     
     
         32 . The apparatus of  claim 31 , wherein the first ranking routine is related to a measure of similarity between a static attribute of the particular promotion and one or more static attributes of one or more other promotions. 
     
     
         33 . The apparatus of  claim 31 , wherein the second ranking routine is related to a measure of correlation between a purchase history attribute of the particular promotion and one or more purchase history attributes of one or more other promotions. 
     
     
         34 . The apparatus of  claim 31 , wherein the second ranking routine is based at least in part on one or more historical co-purchases from a first service associated with the particular promotion over a period of time. 
     
     
         35 . A non-transitory computer readable medium, comprising instructions that when executed on one or more computers cause the one or more computers to:
 receive promotion data describing a set of promotions;   cause rendering of an electronic user interface to a first consumer device associated with a first consumer, the electronic user interface comprising a plurality of impressions, wherein the plurality of impressions are respectively associated with a displayed promotion subset of the set of promotions;   receive clickstream data indicating real time interaction by the first consumer with a particular impression of the plurality of impressions, wherein the particular impression is associated with a particular promotion;   generate a ranked set of promotions based at least in part on the promotion data and the particular promotion, wherein the ranked set of promotions is based at least in part on adaptive collaborative filtering signals and static similarity signals; and   cause updating of the electronic user interface to display an updated plurality of impressions associated with the ranked set of promotions simultaneously with and positioned proximate to the particular impression associated with the particular promotion.   
     
     
         36 . The non-transitory computer readable medium of  claim 35 , wherein the group of cross-sell widgets comprises a user-specific recommendations widget that collects signals based on recent purchase history. 
     
     
         37 . The non-transitory computer readable medium of  claim 35 , wherein the group of cross-sell widgets comprises a views-based conversion widget that collects signals describing a portion of consumers that went on to buy the particular promotion relative to other viewed promotions. 
     
     
         38 . The non-transitory computer readable medium of  claim 35 , wherein the group of cross-sell widgets comprises a purchase-based widget that collects signals describing a portion of consumers that went on to buy the particular promotion relative to other purchased promotions. 
     
     
         39 . The non-transitory computer readable medium of  claim 35 , wherein the group of cross-sell widgets comprises a search history widget that collects signals describing the first consumer's search history. 
     
     
         40 . The non-transitory computer readable medium of  claim 35 , wherein the group of cross-sell widgets comprise a newly launched promotions widget that collects signals describing newly launched promotions relevant to the first consumer.