Generating optimized in-channel and cross-channel promotion recommendations using free shipping qualifier

• US 10,699,299 B1
• Filed: 04/22/2015
• Issued: 06/30/2020
• Est. Priority Date: 04/22/2014
• Status: Active Grant

• Current Assignee: Groupon Incorporated
• Original Assignee: Groupon Incorporated
• Inventors: Hou, Feili, Tripathi, Vyomkesh, Agarwal, Nipun, Parekh, Rajesh Girish
• Primary Examiner(s): Andrei, Radu
• Application Number:
  US14/693,721
• Time in Patent Office: 1,896 Days
• CPC Class Codes: G06F 16/24578 using ranking
• CPC Class Codes: G06F 16/955 using information identifiers, e.g. uniform resource locators [URL]
• CPC Class Codes: G06Q 30/02 Marketing; Price estimation or determination; Fundraising
• CPC Class Codes: G06Q 30/0255 based on user history
• CPC Class Codes: G06Q 30/0269 based on user profile or attribute
• CPC Class Codes: G06Q 30/0277 Online advertisement

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.

Claims

1. A computer-implemented method for implementing free shipping promotions ranking, the method comprising:

receiving, by a processor, promotion data describing a set of promotions, wherein the promotion data include promotion attributes and metadata associated with the promotions, and wherein the set of promotions includes a particular promotion currently being purchased by a first consumer;

generating, by the processor, a ranked set of promotions based on (i) the promotion data, (ii) historical co-purchases associated with the particular promotion over a period of time, wherein each of the historical co-purchases represents a purchase, by another consumer of a plurality of consumers, of both the particular promotion from a first service and a second promotion from a second service within the period of time, and wherein each promotion of the ranked set of promotions is associated with promotion attributes that differ from promotion attributes associated with the particular promotion, (iii) a co-view score, and (iv) cross-sell signals received from at least one of a group of cross-sell widgets, wherein the ranked set of promotions comprises at least one collaborative filtering ranked list and at least one static similarity ranked list;

generating, by the processor, a set of recommended promotions for the first consumer by selecting a subset of the ranked set of promotions;

optimizing, by the processor, the set of recommended promotions for the first consumer based on real-time inputs and a free shipping qualifier threshold amount, the set of recommended promotions optimized to enable the first consumer'"'"'s purchase cart total to reach an amount that either meets or exceeds the free shipping qualifier threshold amount; and

transmitting, by the processor, to the first consumer the set of recommended promotions as optimized for display within a user interface.

2. The method of claim 1, wherein optimizing the set of recommended promotions for the first consumer based on a free shipping qualifier threshold amount comprises:

selecting, by the processor, a subset of the recommended promotions that each meet a price constraint, wherein the price constraint is a sum of the promotion price and a current purchase cart total of the first consumer being greater than the shipping qualifier threshold amount and less than a sum of the shipping qualifier threshold amount plus an increment; and

in an instance in which the subset of the top-ranked promotions is smaller than a threshold quantity of promotions,

selecting, by the processor and based in part on the price constraint, additional promotions by selecting one up to a maximum quantity of promotions from each of a set of services respectively associated with at least one of the set of a ranked list of promotions.

3. The method of claim 1, wherein the group of cross-sell widgets include a user-specific recommendations widget that collects signals based on recent purchase history, a views-based conversion widget that collects signals describing a portion of consumers that went on to buy the particular promotion versus other viewed promotions, a purchase-based widget that collects signals describing a portion of consumers that went on to buy the particular promotion versus other purchased promotions, a search history widget that collects signals describing a consumer'"'"'s search history, and a newly launched promotions widget that collects signals describing newly launched promotions relevant to a consumer.

4. The method of claim 3, further comprising:

calculating, by the processor and using the promotion data, a co-purchase score for each of the promotions associated with a second service based in part on calculating a frequency of purchases by consumers of promotions associated with the first service and purchases by those same consumers of promotions associated with the second service.

5. The method of claim 4, wherein calculating the co-purchase frequency comprises:

calculating, by the processor, probability distribution and Jaccard scores for each promotion service based on a ratio of a number of consumers who purchased promotions from both the first service and the second service to a sum of a number of consumers who purchased promotions only from the first service and a number of consumers who purchased promotions only from the second service, wherein the sum includes a subtraction of the number of consumer who purchased promotions from both the first service and the second service.

6. The method of claim 4, further comprising:

generating, by the processor, a ranked list of promotions by ranking the promotions in descending order of their respective co-purchase scores.

7. The method of claim 6, further comprising:

selecting, by the processor, a subset of the top-ranked promotions in the ranked list for recommendation to the first consumer;

in an instance in which the subset of the top-ranked promotions is smaller than a threshold quantity of promotions,

select, by the processor and using the promotion data, a set of top revenue-earning freshly launched promotions; and

backfilling, by the processor, the selected subset of the top-ranked promotions using the set of top revenue-earning freshly launched promotions.

8. A computer program product, stored on a 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, wherein the promotion data include promotion attributes and metadata associated with the promotions, and wherein the set of promotions includes a particular promotion currently being purchased by a first consumer;

generate a ranked set of promotions based on (i) the promotion data, (ii) historical co-purchases associated with the particular promotion over a period of time, wherein each of the historical co-purchases represents a purchase by another consumer of a plurality of consumers, of both the particular promotion from a first service and a second promotion from a second service within the period of time, and wherein each promotion of the ranked set of promotions is associated with promotion attributes that differ from promotion attributes associated with the particular promotion, (iii) a co-view score, and (iv) cross-sell signals received from at least one of a group of cross-sell widgets, wherein the ranked set of promotions comprises at least one collaborative filtering ranked list and at least one static similarity ranked list;

generate a set of recommended promotions for the first consumer by selecting a subset of the ranked set of promotions;

optimize the set of recommended promotions for the first consumer based on real-time inputs and a free shipping qualifier threshold amount, the set of recommended promotions optimized to enable the first consumer'"'"'s purchase cart total to reach an amount that either meets or exceeds the free shipping qualifier threshold amount; and

transmit to the first consumer the set of recommended promotions as optimized for display within a user interface.

9. The computer program product of claim 8, wherein optimizing the set of recommended promotions for the first consumer based on a free shipping qualifier threshold amount comprises:

selecting a subset of the recommended promotions that each meet a price constraint, wherein the price constraint is a sum of the promotion price and a current purchase cart total of the first consumer being greater than the shipping qualifier threshold amount and less than a sum of the shipping qualifier threshold amount plus an increment; and

in an instance in which the subset of the top-ranked promotions is smaller than a threshold quantity of promotions,

selecting, based in part on the price constraint, additional promotions by selecting one up to a maximum quantity of promotions from each of a set of services respectively associated with at least one of the set of a ranked list of promotions.

10. The computer program product of claim 8, wherein the group of cross-sell widgets include a user-specific recommendations widget that collects signals based on recent purchase history, a views-based conversion widget that collects signals describing a portion of consumers that went on to buy the particular promotion versus other viewed promotions, a purchase-based widget that collects signals describing a portion of consumers that went on to buy the particular promotion versus other purchased promotions, a search history widget that collects signals describing a consumer'"'"'s search history, and a newly launched promotions widget that collects signals describing newly launched promotions relevant to a consumer.

11. The computer program product of claim 10, further comprising instructions that when executed on one or more computers cause the one or more computers to:

calculate, using the promotion data, a co-purchase score for each of the promotions associated with a second service based in part on calculating a frequency of purchases by consumers of promotions associated with the first service and purchases by those same consumers of promotions associated with the second service.

12. The computer program product of claim 11, wherein calculating the co-purchase frequency comprises:

calculating probability distribution and Jaccard scores for each promotion service based on a ratio of a number of consumers who purchased promotions from both the first service and the second service to a sum of a number of consumers who purchased promotions only from the first service and a number of consumers who purchased promotions only from the second service, wherein the sum includes a subtraction of the number of consumer who purchased promotions from both the first service and the second service.

13. The computer program product of claim 10, further comprising instructions that when executed on one or more computers cause the one or more computers to:

generate a ranked list of promotions by ranking the promotions in descending order of their respective co-purchase scores.

14. The computer program product of claim 13, further comprising instructions that when executed on one or more computers cause the one or more computers to:

select a subset of the top-ranked promotions in the ranked list for recommendation to the first consumer;

in an instance in which the subset of the top-ranked promotions is smaller than a threshold quantity of promotions,

select, using the promotion data, a set of top revenue-earning freshly launched promotions; and

backfill the selected subset of the top-ranked promotions using the set of top revenue-earning freshly launched promotions.

15. A system, comprising:

one or more computers and one or more storage devices storing instructions that are operable, when executed by the one or more computers, to cause the one or more computers to;

receive promotion data describing a set of promotions, wherein the promotion data include promotion attributes and metadata associated with the promotions, and wherein the set of promotions includes a particular promotion currently being purchased by a first consumer;

generate a ranked set of promotions based on (i) the promotion data, (ii) historical co-purchases associated with the particular promotion over a period of time, wherein each of the historical co-purchases represents a purchase, by another consumer of a plurality of consumers, of both the particular promotion from a first service and a second promotion from a second service within the period of time, and wherein each promotion of the ranked set of promotions is associated with promotion attributes that differ from promotion attributes associated with the particular promotion, (iii) a co-view score, and (iv) cross-sell signals received from at least one of a group of cross-sell widgets, wherein the ranked set of promotions comprises at least one collaborative filtering ranked list and at least one static similarity ranked list;

generate a set of recommended promotions for the first consumer by selecting a subset of the ranked set of promotions;

optimize the set of recommended promotions for the first consumer based on real-time inputs and a free shipping qualifier threshold amount, the set of recommended promotions optimized to enable the first consumer'"'"'s purchase cart total to reach an amount that either meets or exceeds the free shipping qualifier threshold amount; and

transmit to the first consumer the set of recommended promotions as optimized for display within a user interface.

16. The system of claim 15, wherein optimizing the set of recommended promotions for the first consumer based on a free shipping qualifier threshold amount comprises:

selecting a subset of the recommended promotions that each meet a price constraint, wherein the price constraint is a sum of the promotion price and a current purchase cart total of the first consumer being greater than the shipping qualifier threshold amount and less than a sum of the shipping qualifier threshold amount plus an increment; and

in an instance in which the subset of the top-ranked promotions is smaller than a threshold quantity of promotions,

selecting, based in part on the price constraint, additional promotions by selecting one up to a maximum quantity of promotions from each of a set of services respectively associated with at least one of the set of a ranked list of promotions.

17. The system of claim 15, wherein the group of cross-sell widgets include a user-specific recommendations widget that collects signals based on recent purchase history, a views-based conversion widget that collects signals describing a portion of consumers that went on to buy the particular promotion versus other viewed promotions, a purchase-based widget that collects signals describing a portion of consumers that went on to buy the particular promotion versus other purchased promotions, a search history widget that collects signals describing a consumer'"'"'s search history, and a newly launched promotions widget that collects signals describing newly launched promotions relevant to a consumer.

18. The system of claim 17, further comprising instructions that when executed on one or more computers cause the one or more computers to:

calculate, using the promotion data, a co-purchase score for each of the promotions associated with a second service based in part on calculating a frequency of purchases by consumers of promotions associated with the first service and purchases by those same consumers of promotions associated with the second service.

19. The system of claim 18, further comprising instructions that when executed on one or more computers cause the one or more computers to:

generate a ranked list of promotions by ranking the promotions in descending order of their respective co-purchase scores.

20. The system of claim 19, further comprising instructions that when executed on one or more computers cause the one or more computers to:

select a subset of the top-ranked promotions in the ranked list for recommendation to the first consumer;

in an instance in which the subset of the top-ranked promotions is smaller than a threshold quantity of promotions,

select, using the promotion data, a set of top revenue-earning freshly launched promotions; and

backfill the selected subset of the top-ranked promotions using the set of top revenue-earning freshly launched promotions.