Predictive recommendation system using absolute relevance
In general, embodiments of the present invention provide systems, methods and computer readable media for ranking promotions selected for recommendation to consumers based on predictions of promotion performance and consumer behavior. In embodiments, a set of promotions to be recommended to a consumer can be sorted and/or ranked according to respective relevance scores representing a probability that the consumer's behavior in response to the promotion will match a ranking target. In embodiments, calculating scores is based on a relevance model (a predictive function) derived from one or more contextual data sources representing attributes of promotions and consumer behavior. In embodiments, an absolute relevance score represents an absolute prediction of a ranking target variable. In embodiments, absolute relevance may be used to determine personalized local merchant discovery frontiers; featured result set thresholding for impressions; and/or promotion notification triggers. In embodiments, predictive models based on gross revenue may be optimized using promotion category-dependent price boosting.
1. 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:
generate, based at least in part on one or more attributes associated with a consumer identifier and one or more other attributes associated with respective promotions of a plurality of promotions, a relevance score for each respective promotion of the plurality of promotions;
determine a promotions subset from the plurality of promotions, wherein promotions of the promotions subset comprise a respective relevance score above a relevance threshold;
determine an optimal promotion category level for the consumer identifier based at least in part on a consumer location associated with the consumer identifier and a count of promotions in the promotions subset;
rank the promotions in the promotions subset based at least in part on the optimal promotion category level to determine a ranked promotions subset; and
transmit at least a portion of the ranked promotions subset to a computing device associated with the consumer identifier.
2. The system of claim 1 , wherein the one or more storage devices store instructions that are operable, when executed by the one or more computers, to further cause the one or more computers to:
receive, from the computing device, a ranking target variable; and
generate the relevance score based at least in part on the ranking target variable.
3. The system of claim 1 , wherein the one or more storage devices store instructions that are operable, when executed by the one or more computers, to further cause the one or more computers to:
for each respective promotion of the plurality of promotions,
determine a promotion price and a promotion category for the respective promotion; and
compare the promotion price to a price threshold associated with the promotion category.
4. The system of claim 3 , wherein the one or more storage devices store instructions that are operable, when executed by the one or more computers, to further cause the one or more computers to:
in response to a determination that the promotion price satisfies the price threshold,
adjust the relevance score for the respective promotion based at least in part on the promotion price.
5. The system of claim 1 , wherein the one or more storage devices store instructions that are operable, when executed by the one or more computers, to further cause the one or more computers to:
generate the relevance score based at least in part on a relevance model configured based at least in part on contextual data sources associated with at least one location.
6. The system of claim 1 , wherein the one or more storage devices store instructions that are operable, when executed by the one or more computers, to further cause the one or more computers to:
generate the relevance score based at least in part on a relevance model configured based at least in part on contextual data sources associated with at least one category of interest.
7. The system of claim 1 , wherein the one or more storage devices store instructions that are operable, when executed by the one or more computers, to further cause the one or more computers to:
generate the relevance score based at least in part on at least a first random forest model associated with a first contextual data source and a second random forest model associated with a second contextual data source.
8. The system of claim 1 , wherein the consumer location is a current consumer location associated with the computing device, and wherein the one or more storage devices store instructions that are operable, when executed by the one or more computers, to further cause the one or more computers to:
determine the optimal promotion category level for the consumer identifier based at least in part on a current consumer location and the count of promotions in the promotions subset.
9. The system of claim 1 , wherein the consumer location is a prior consumer location associated with the consumer identifier, and wherein the one or more storage devices store instructions that are operable, when executed by the one or more computers, to further cause the one or more computers to:
determine the optimal promotion category level for the consumer identifier based at least in part on the prior consumer location and the count of promotions in the promotions subset.
10. The system of claim 1 , wherein the consumer location is a potential consumer location associated with a geographic region, and wherein the one or more storage devices store instructions that are operable, when executed by the one or more computers, to further cause the one or more computers to:
determine the optimal promotion category level for the consumer identifier based at least in part on the potential consumer location and the count of promotions in the promotions subset.
11. A computer-implemented method, comprising:
generating, by a device comprising a processor and based at least in part on one or more attributes associated with a consumer identifier and one or more other attributes associated with respective promotions of a plurality of promotions, a relevance score for each respective promotion of the plurality of promotions;
determining, by the device, a promotions subset from the plurality of promotions, the promotions of the promotions subset comprising a respective relevance score above a relevance threshold;
determining, by the device, an optimal promotion category level for the consumer identifier based at least in part on a consumer location associated with the consumer identifier and a count of promotions in the promotions subset;
ranking, by the device, the promotions in the promotions subset based at least in part on the optimal promotion category level to determine a ranked promotions subset; and
transmitting, by the device, at least a portion of the ranked promotions subset to a computing device associated with the consumer identifier.
12. The computer-implemented method of claim 11 , further comprising:
receiving, by the device and from the computing device, a ranking target variable; and
generating, by the device, the relevance score based at least in part on the ranking target variable.
13. The computer-implemented method of claim 11 , further comprising:
for each respective promotion of the plurality of promotions,
determining, by the device, a promotion price and a promotion category for the respective promotion; and
comparing, by the device, the promotion price to a price threshold associated with the promotion category.
14. The computer-implemented method of claim 13 , further comprising:
in response to a determination that the promotion price satisfies the price threshold,
adjusting, by the device, the relevance score for the respective promotion based at least in part on the promotion price.
15. The computer-implemented method of claim 11 , wherein the generating the relevance score comprises generating the relevance score based at least in part on a relevance model configured based at least in part on contextual data sources associated with at least one location.
16. The computer-implemented method of claim 11 , wherein the generating the relevance score comprises generating the relevance score based at least in part on a relevance model configured based at least in part on contextual data sources associated with at least one category of interest.
17. The computer-implemented method of claim 11 , wherein the generating the relevance score comprises generating the relevance score based at least in part on at least a first random forest model associated with a first contextual data source and a second random forest model associated with a second contextual data source.
18. A computer program product, stored on a computer readable medium, comprising instructions that when executed by one or more computers cause the one or more computers to:
generate, based at least in part on one or more attributes associated with a consumer identifier and one or more other attributes associated with respective promotions of a plurality of promotions, a relevance score for each respective promotion of the plurality of promotions;
determine a promotions subset from the plurality of promotions, wherein promotions of the promotions subset comprise a respective relevance score above a relevance threshold;
determine an optimal promotion category level for the consumer identifier based at least in part on a consumer location associated with the consumer identifier and a count of promotions in the promotions subset;
rank the promotions in the promotions subset based at least in part on the optimal promotion category level to determine a ranked promotions subset; and
transmit at least a portion of the ranked promotions subset to a computing device associated with the consumer identifier.
19. The computer program product of claim 18 , further comprising instructions that when executed by the one or more computers cause the one or more computers to:
for each respective promotion of the plurality of promotions,
determine a promotion price and a promotion category for the respective promotion; and
compare the promotion price to a price threshold associated with the promotion category.
20. The computer program product of claim 19 , further comprising instructions that when executed by the one or more computers cause the one or more computers to:
in response to a determination that the promotion price satisfies the price threshold, adjust the relevance score for the respective promotion based at least in part on the promotion price.