Automated and optimal promotional experimental test designs incorporating constraints

• US 9,940,639 B2
• Filed: 03/31/2014
• Issued: 04/10/2018
• Est. Priority Date: 03/13/2013
• Status: Active Grant

• Current Assignee: Maplebear Inc.
• Original Assignee: Eversight, Inc. (Maplebear Inc.)
• Inventors: Moran, David, Montero, Michael
• Primary Examiner(s): Brown, Luis A
• Assistant Examiner(s): Andrei, Radu
• Application Number:
  US14/231,432
• Publication Number:
  US 20140330634A1
• Time in Patent Office: 1,471 Days
• CPC Class Codes: G06F 3/0481 based on specific properties of the displayed interaction object or a metaphor-based environment, e.g. interaction with desktop elements like windows or icons, or assisted by a cursor's changing behaviour or appearance
• CPC Class Codes: G06F 3/0485 Scrolling or panning
• CPC Class Codes: G06F 3/0488 using a touch-screen or digitiser, e.g. input of commands through traced gestures
• CPC Class Codes: G06Q 30/02 Marketing; Price estimation or determination; Fundraising
• CPC Class Codes: G06Q 30/0244 Optimization
• CPC Class Codes: G06Q 30/0267 Wireless devices
• CPC Class Codes: G06T 11/60 Editing figures and text; Combining figures or text
• CPC Class Codes: H04L 65/403 Arrangements for multi-party communication, e.g. for conferences data switching systems for conference H04L12/18; arrangements for connecting several subscribers to a common circuit, i.e. affording conference facilities H04M3/56; television conferencing systems H04N7/15
• CPC Class Codes: H04M 1/724 User interfaces specially adapted for cordless or mobile telephones
• CPC Class Codes: H04N 21/47 End-user applications

Abstract

Methods and apparatus for implementing forward looking optimizing promotions by administering, in large numbers and iteratively, test promotions formulated using highly granular test variables and automatically incorporating constraints on segmented subpopulations. The responses from individuals in the subpopulations are received and analyzed. The analysis result is employed to subsequently formulate a general public promotion.

Claims

1. A computer-implemented method for performing promotion optimization incorporating constraints, comprising:

receiving a set of variables for promotional campaign, and a set of variable values for each of the variables;

generating a design space for the promotional campaign where all permutations of the variable values are represented;

filtering the design space to reduce permutations of a plurality of test promotions to enable testing of the test promotions in a testing time period, wherein the testing time period includes concurrent testing of a subset of the plurality of test promotions, the filtering using a filtering system comprising;

a user computer for generating a request for test promotions for the given set of variables;

two filtering schemes including inclusion/exclusion method and factor grouping method;

a plurality of logical filtering elements comprising constraints;

a server coupled to the user computer and an Internet computer network, the server associated with the two filtering schemes and the plurality of filtering elements, the server further receiving the request for the test promotions from the user computer, selecting between the inclusion/exclusion method and the factor grouping method responsive to the balance of the design space, wherein balance of the design space is defined by a matrix of variable values for the design space where each column of the matrix includes an equal number of each variable value, and wherein the inclusion/exclusion method is defined as applying the plurality of constraints to the design space and removing or including variable value combinations which satisfy all the plurality of constraints, and further wherein the factor grouping method is defined as generating a meta-variable for replacing a subset of the variables that are impacted by any of the plurality of constraints, and factoring the combination of these subset of the variables into a smaller combination of meta-variable values comporting to the plurality of constraints, wherein the selection between the two filtering schemes preferences the inclusion/exclusion method when the set of variable values is below a threshold number and preferences the factor grouping method when the set of variable values is at or above the threshold number, and executing the selected filtering scheme by combining the scheme with the associated filtering elements to reduce the design space in order to reduce computational demands while maintaining experimental integrity;

generating the plurality of test promotions using the reduced design space;

administering the plurality of test promotions to a plurality of segmented subpopulations of consumers to improve statistical validity of correlations made between the variable values;

obtaining responses from said segmented subpopulations of; and

generating a general population promotion responsive to analysis of said responses, including the correlations made between variable values.

2. The method of claim 1, wherein at least one of the plurality of constraints is exclusionary, wherein exclusionary constraints prevent certain combinations.

3. The method of claim 1, wherein at least one of the plurality of constraints is inclusionary, wherein inclusionary constraints require certain combinations.

4. The method of claim 1, wherein at least one of the plurality of constraints is hybrid, wherein hybrid constraints include an exclusionary element and an inclusionary element.

5. The method of claim 1, wherein at least two of the constraints are combined into a canonical rule.

6. The method of claim 1, wherein the plurality of constraints are incorporated into the plurality of test promotions in a manner that allows statistically meaningful analysis of each variable value'"'"'s contribution.

7. The method of claim 6, wherein the inclusion/exclusion method is applied if the reduced design space under this method is balanced and there is even distribution between pairs of variable values.

8. The method of claim 7, wherein factor grouping method is applied if the inclusion/exclusion method is unable to yield the reduced design space that is balanced and there is even distribution between pairs of variable values.