Highly scalable internet-based parallel experiment methods and apparatus for obtaining insights from test promotion results

• US 10,460,339 B2
• Filed: 03/03/2015
• Issued: 10/29/2019
• Est. Priority Date: 03/03/2015
• Status: Active Grant

• Current Assignee: Maplebear Inc.
• Original Assignee: Eversight, Inc. (Maplebear Inc.)
• Inventors: Moran, David
• Primary Examiner(s): Andrei, Radu
• Application Number:
  US14/636,528
• Publication Number:
  US 20170039590A1
• Time in Patent Office: 1,701 Days
• CPC Class Codes: G06Q 30/0201 Market modelling; Market analysis; Collecting market data
• CPC Class Codes: G06Q 30/0244 Optimization
• CPC Class Codes: G06Q 30/0269 based on user profile or attribute
• CPC Class Codes: G06Q 30/0277 Online advertisement
• CPC Class Codes: H04L 67/02 based on web technology, e.g. hypertext transfer protocol [HTTP]
• CPC Class Codes: H04N 21/41415 involving a public display, viewable by several users in a public space outside their home, e.g. movie theatre, information kiosk

Abstract

Methods and apparatus for conducting test promotions in a highly scalable and cost-effective manner using parallel experiment methodology are disclosed. Test promotions are presented to visitors of a website in a parallel experiment manner wherein each page presents one test promotion to isolate the test promotions from one another. The visitors'"'"' responses with respect to the test promotion are then recorded and analyzed to determine the performance of the test promotion.

Claims

1. A computer-implemented method for performing promotion optimization that is performed by a promotion optimization system including a processor, containing a promotion module, an administration module, and a monitoring module, the method comprising:

generating a plurality of test promotions for a plurality of products from a plurality of manufacturers;

selecting a subset of the plurality of test promotions as promotions of interest;

administering the plurality of test promotions to a plurality of segmented subpopulations of consumers through a webpage where a single one of the promotions of interest is displayed together with a fixed selection of the plurality of test promotions to a given subpopulation of consumers in real-time, wherein the real-time administration of test promotions includes concurrent testing of the plurality of test promotions, and wherein the single one of the promotions of interest is randomized upon each viewing of the webpage;

obtaining responses from said segmented subpopulations of consumers;

tracking the obtained responses for each consumer over time and across different test promotions;

analyzing the tracked obtained responses to generate insights, wherein the insights are relative performance of the single one of the promotions of interest in achieving a desired response from the segmented subpopulations of consumers; and

generating a general population promotion using the promotion optimization system to at least one of gain market share, increase revenue and increase profit using the insights.

2. The method of claim 1, wherein the insights include determining combinations of variable values within a given test promotion that increases profit, volume or market share.

3. The method of claim 1, wherein the insights include different combinations of the test promotions.

4. The method of claim 1, wherein the insights include different orders of the test promotions.

5. The method of claim 1, wherein the tracking utilizes single sign on.

6. The method of claim 1, wherein the tracking utilizes web cookies.

7. The method of claim 1, wherein the tracking utilizes biometric data.

8. The method of claim 1, wherein the tracking utilizes a username.

9. The method of claim 1, further comprising assigning a subset of the test promotions to each consumer and repeatedly displaying said assigned subset of test promotions to the associated consumer along with randomized test promotions over time.

10. The method of claim 9, wherein the assigned subset of promotions are displayed in randomized locations on the webpage each time they are displayed to the consumer.