Method, apparatus, and computer program product for setting a benchmark conversion rate

• US 10,242,373 B1
• Filed: 06/26/2014
• Issued: 03/26/2019
• Est. Priority Date: 10/04/2012
• Status: Active Grant

• Current Assignee: Groupon Incorporated
• Original Assignee: Groupon Incorporated
• Inventors: Shariff, Shafiq, Nordquist, Derek
• Primary Examiner(s): Gills, Kurtis
• Application Number:
  US14/316,264
• Time in Patent Office: 1,734 Days
• CPC Class Codes: G06Q 30/0202 Market predictions or forecasting for commercial activities
• CPC Class Codes: G06Q 30/0261 based on user location

Abstract

Provided herein are systems, methods and computer readable media for setting a benchmark conversion rate. An example method comprises accessing user search data, the user search data generated by a user interacting with a promotion and marketing service to identify a requested promotion, generating an identification pair for the search data, the identification pair comprising an identification of a promotion tuple and a geographic subdivision, generating a search velocity based on the generated identification pairs, accessing a conversion rate for the promotion tuple in a plurality of geographic subdivisions and setting a benchmark rate for a promotion tuple, the benchmark rate corresponding to the conversion rate of a subdivision of the plurality of subdivisions based on the subdivision satisfying at least one of a search velocity threshold, a prime merchant metric threshold or a conversion rate threshold.

Claims

1. A method for utilizing a real-time determination of an achievable conversion rate to determine one or more particular merchants from among particular merchant classes to target and how many additional units will sell, the determination, in real-time, of the achievable conversion rate utilizing data from one or more subdivisions located in different geographic regions, and automatically includes one or more particular subdivisions and excludes one or more other particular subdivisions, the method comprising:

accessing, in real-time, user search data, the user search data generated by a user interacting with a promotion and marketing service to identify a requested promotion, the user search data comprising at least location specific data;

generating an identification pair for the search data, the identification pair comprising a first classification and a second classification, the first classification identifying a promotion tuple, comprising at least a category of promotion, and the second classification identifying a location identified by the location specific data,

the first classification and the second classification generated by;

normalizing the user search data, supplying the normalized user search data to a classifying model as attribute data, wherein the classifying model is a trainable classifier adapted based on a training data set of exemplary data representing exemplary terms previously determined to be semantically related to particular categories, and

generating a search velocity based on the generated identification pairs;

accessing a conversion rate for the promotion tuple in a plurality of different geographic subdivisions;

setting a benchmark rate for a promotion tuple, the benchmark rate configured for establishing a benchmark conversion rate for each of one or more identification pairs to estimate an achievable conversion rate in a given identification pair when that identification pair were stocked with adequate supply,

wherein the benchmark rate corresponding to the conversion rate of a different subdivision of the plurality of different subdivisions based on the different subdivision satisfying at least one of a search velocity threshold, a prime merchant metric threshold or a conversion rate threshold,

wherein the benchmark rate is set to a maximum conversion rate from one of (a) an average conversion rate for the promotion tuple in a peer group of different subdivisions or (b) a pre-defined percentile of all conversion rates for the promotion tuple across all subdivisions in the peer group;

identifying one or more providers in the subdivision having the benchmark rate;

transmitting information identifying the one or more providers to a lead generation module; and

generating a prioritized call list for each of one or more sales resources, the prioritized call list comprising information identifying the one or more providers.

2. The method according to claim 1, further comprising:

analyzing a subdivision; and

generating two or more regions within the subdivision based on one or more of subscriber density or population density.

3. The method according to claim 1, wherein the benchmark rate corresponding to the conversion rate of a subdivision of the plurality of subdivisions is further based on the subdivision satisfying an inventory threshold.

4. The method according to claim 1, wherein the benchmark rate corresponding to the conversion rate of a subdivision of the plurality of subdivisions is further based on the subdivision satisfying a prime merchant metric threshold.

5. The method according to claim 1, the benchmark rate corresponding to a predefined percentile of one or more conversion rates of a plurality of subdivisions of a division peer group in an instance in which user search data fails to meet a predetermined threshold.

6. The method according to claim 1, the benchmark rate corresponding to a conversion rate of a second identification pair meeting a given set of supply conditions, the identification pair corresponding to a subdivision of a division peer group, in an instance in which user search data fails to meet a predetermined threshold.

7. A computer program product for utilizing a real-time determination of an achievable conversion rate to determine one or more particular merchants from among particular merchant classes to target and how many additional units will sell, the determination, in real-time, of the achievable conversion rate utilizing data from one or more subdivisions located in different geographic regions, and automatically includes one or more particular subdivisions and excludes one or more other particular subdivisions, the computer program product comprising at least one non-transitory computer-readable storage medium having computer-executable program code instructions stored therein, the computer-executable program code instructions comprising program code instructions for:

accessing, in real-time, user search data, the user search data generated by a user interacting with a promotion and marketing service to identify a requested promotion, the user search data comprising at least location specific data;

generating an identification pair for the search data, the identification pair comprising a first classification and a second classification, the first classification identifying a promotion tuple, comprising at least a category of promotion, and the second classification identifying a location identified by the location specific data,

the first classification and the second classification generated by;

normalizing the user search data, supplying the normalized user search data to a classifying model as attribute data, wherein the classifying model is a trainable classifier adapted based on a training data set of exemplary data representing exemplary terms previously determined to be semantically related to particular categories,

generating a search velocity based on the generated identification pairs;

accessing a conversion rate for the promotion tuple in a plurality of different geographic subdivisions;

setting a benchmark rate for a promotion tuple, the benchmark rate configured for establishing a benchmark conversion rate for each of one or more identification pairs to estimate an achievable conversion rate in a given identification pair when that identification pair were stocked with adequate supply,

wherein the benchmark rate corresponding to the conversion rate of a different subdivision of the plurality of different subdivisions based on the different subdivision satisfying at least one of a search velocity threshold, a prime merchant metric threshold or a conversion rate threshold,

wherein the benchmark rate is set to a maximum conversion rate from one of (a) an average conversion rate for the promotion tuple in a peer group of different subdivisions or (b) a pre-defined percentile of all conversion rates for the promotion tuple across all subdivisions in the peer group;

identifying one or more providers in the subdivision having the benchmark rate;

transmitting information identifying the one or more providers to a lead generation module; and

generating a prioritized call list for each of one or more sales resources, the prioritized call list comprising information identifying the one or more providers.

8. The computer program product according to claim 7, wherein the computer-executable program code instructions further comprise program code instructions for:

analyzing a subdivision; and

generating two or more regions within the subdivision based on one or more of subscriber density or population density.

9. The computer program product according to claim 7, wherein the benchmark rate corresponding to the conversion rate of a subdivision of the plurality of subdivisions is further based on the subdivision satisfying an inventory threshold.

10. The computer program product according to claim 7, wherein the benchmark rate corresponding to the conversion rate of a subdivision of the plurality of subdivisions is further based on the subdivision satisfying a prime merchant metric threshold.

11. The computer program product according to claim 7, the benchmark rate corresponding to a predefined percentile of one or more conversion rates of a plurality of subdivisions of a division peer group in an instance in which user search data fails to meet a predetermined threshold.

12. The computer program product according to claim 7, the benchmark rate corresponding to a conversion rate of a second identification pair meeting a given set of supply conditions, the identification pair corresponding to a subdivision of a division peer group, in an instance in which user search data fails to meet a predetermined threshold.

13. An apparatus for utilizing a real-time determination of an achievable conversion rate to determine one or more particular merchants from among particular merchant classes to target and how many additional units will sell, the determination, in real-time, of the achievable conversion rate utilizing data from one or more subdivisions located in different geographic regions, and automatically includes one or more particular subdivisions and excludes one or more other particular subdivisions, the apparatus comprising at least one processor and at least one memory including computer program code, the at least one memory and the computer program code configured to, with the processor, cause the apparatus to at least:

access, in real-time, user search data, the user search data generated by a user interacting with a promotion and marketing service to identify a requested promotion, the user search data comprising at least location specific data;

generate an identification pair for the search data, the identification pair comprising a first classification and a second classification, the first classification identifying a promotion tuple, comprising at least a category of promotion, and the second classification identifying a location identified by the location specific data,

the first classification and the second classification generated by;

normalizing the user search data, supplying the normalized user search data to a classifying model as attribute data, wherein the classifying model is a trainable classifier adapted based on a training data set of exemplary data representing exemplary terms previously determined to be semantically related to particular categories, and

generate a search velocity based on the generated identification pairs;

access a conversion rate for the promotion tuple in a plurality of different geographic subdivisions;

set a benchmark rate for a promotion tuple, the benchmark rate configured for establishing a benchmark conversion rate for each of one or more identification pairs to estimate an achievable conversion rate in a given identification pair when that identification pair were stocked with adequate supply,

wherein the benchmark rate corresponding to the conversion rate of a different subdivision of the plurality of different subdivisions based on the different subdivision satisfying at least one of a search velocity threshold, a prime merchant metric threshold or a conversion rate threshold,

wherein the benchmark rate is set to a maximum conversion rate from one of (a) an average conversion rate for the promotion tuple in a peer group of different subdivisions or (b) a pre-defined percentile of all conversion rates for the promotion tuple across all subdivisions in the peer group;

identify one or more providers in the subdivision having the benchmark rate;

transmit information identifying the one or more providers to a lead generation module; and

generate a prioritized call list for each of one or more sales resources, the prioritized call list comprising information identifying the one or more providers.

14. The apparatus according to claim 13, wherein the at least one memory and the computer program code are further configured to, with the processor, cause the apparatus to:

analyze a subdivision; and

generate two or more regions within the subdivision based on one or more of subscriber density or population density.

15. The apparatus according to claim 13, wherein the benchmark rate corresponding to the conversion rate of a subdivision of the plurality of subdivisions is further based on the subdivision satisfying an inventory threshold.

16. The apparatus according to claim 13, wherein the benchmark rate corresponding to the conversion rate of a subdivision of the plurality of subdivisions is further based on the subdivision satisfying a prime merchant metric threshold.

17. The apparatus according to claim 13, the benchmark rate corresponding to a predefined percentile of one or more conversion rates of a plurality of subdivisions of a division peer group in an instance in which user search data fails to meet a predetermined threshold.

18. The apparatus according to claim 13, the benchmark rate corresponding to a conversion rate of a second identification pair meeting a given set of supply conditions, the identification pair corresponding to a subdivision of a division peer group, in an instance in which user search data fails to meet a predetermined threshold.