On-line experimentation

• US 7,308,497 B2
• Filed: 03/14/2005
• Issued: 12/11/2007
• Est. Priority Date: 08/26/1999
• Status: Expired due to Term

• Current Assignee: Accenture Global Services Limited (Accenture PLC)
• Original Assignee: Memetrics Holdings Pty Limited (Accenture PLC)
• Inventors: Louviere, Jordan J., Phillips, Hikaru, Bennett, Jason P.
• Primary Examiner(s): Maung, Zarni
• Application Number:
  US11/080,204
• Publication Number:
  US 20050159921A1
• Time in Patent Office: 1,002 Days
• Field of Search: 709/224, 709/203, 709/217, 709/218, 709/219, 709/223, 705/10, 703/22
• US Class Current: 709/224
• CPC Class Codes: G06Q 30/02 Marketing; Price estimation or determination; Fundraising

Abstract

An automated system for experimentation includes an experiment engine which can define an experiment relating to various treatments for a set of content elements. The experiment engine conducts the experiment over a data network. An observation module collects observation data relating to user behavior for each treatment. A scripting/scheduling engine coordinates the operation of the experiment engine and the observation module.

Claims

1. A computer system for automatically managing delivery of content to users during interactive sessions between the system and users, the computer system comprising:

a computer memory content store to hold a set of digital content elements;

a programmed experiment engine to hold or generate experimental design rules governing the composition of combinations of the content elements to form a variation; and

a programmed allocator module to automatically interact with the programmed experiment engine to retrieve and deliver different discrete, perceptibly-renderable digital variations to the users during the interactive sessions, according to the experimental design rules.

2. A computer system according to claim 1, wherein the rules which govern the delivery of the variations to users are situation specific rules, including experiment rules, prediction rules or user-defined rules.

3. A computer system according to claim 1, wherein the allocator module samples users at user interfaces of the users during an experiment and determines which users will be assigned to receive experimental variations and which will be used as experimental controls.

4. A computer system according to claim 3, wherein the system implements statistical sampling procedures to deliver the different variations to respective users.

5. A computer system according to claim 1, wherein the system conducts different experiments at the same time to increase the likelihood of achieving the predetermined outcome.

6. A computer system according to claim 1, wherein the system conducts different experiments over different user interfaces of users to increase the likelihood of achieving the predetermined outcome.

7. A computer system according to claim 1, further comprising a model engine identifies the degree to which the variations influence the behavior of users.

8. A computer system according to claim 7, wherein the model engine creates one or more behavioral models which provide abstract descriptions of observed user behavior based on recorded actions in response to variations.

9. A computer system according to claim 8, wherein a prediction engine automatically converts the behavioral models into predictive models that predict the likelihood of future actions by users in response to variations.

10. A computer system according to claim 9, wherein the prediction engine uses the predictive models to determine a variation for achieving the predetermined outcome, and recommends that variation for delivery to users.

11. A computer system according to claim 10, wherein the allocation module delivers the recommended variation.

12. A computer system according to claim 9, wherein the prediction engine automatically modifies a variation using the predictive models, to influence the likelihood of achieving the predetermined outcome when a future user is presented with that modified content item by the allocator module.

13. A computer system according to claim 9, wherein the system dynamically segments users into a plurality of segments each of which comprises users with similar behavioral characteristics.

14. A computer system according to claim 13, wherein the content store collects and holds data about users from extrinsic databases.

15. A computer system according to claim 13, wherein the prediction engine also generates prediction rules for targeting specific content to particular segments.

16. A computer system according to claim 1, wherein it further comprises a scripting/scheduling engine to automate the operation of the entire system by using the recorded information to generate new variations, new rules governing the systematic variation of the elemental components, and new rules governing the delivery of the variations to users.

17. A computer system according to claim 16, wherein the experiment engine generates new experiments by determining the number of variations, the number of content elements in each variation, the specific content variations that will be delivered during the experiments, and the number of deliveries of the variations that will be made to users.

18. A computer system according to claim 1, wherein all the steps are repeated to iteratively improve the information to relate the variations to the likelihood of the predetermined outcome more accurately.

19. The system of claim 1 further comprising a programmed observation module to record information about the actions taken by the users in response to the treatments delivered during the experiment, and to relate the treatments to the likelihood of a predetermined outcome.

20. A computer system according to claim 1 wherein the system determines which users to include in experiments based on the user profiling.

21. A computer system according to claim 1 wherein the system determines when to include users in experiments based on rules contained within the programmed experiment engine or programmed allocator module.

22. A computer system according to claim 1 where the digital content elements can be assembled to generate digital video.

23. A computer system according to claim 1 where the digital content elements can be assembled to generate advertisements.

24. A computer system according to claim 1 where the digital content elements can be assembled to generate web pages.

25. A computer system according to claim 1 where the digital content elements can be assembled to generate offers.

26. A method for automatically managing delivery of content to users during interactive sessions between the system and users, the computer system comprising:

providing a computer memory content store holding a set of digital content elements, the content store being in communication with a programmed experiment engine that holds or generates experimental design rules governing the composition of combinations of the content elements in the memory store to form a variation;

providing a programmed allocator module, in communication with the programmed experiment engine, to automatically interact with the programmed experiment engine to retrieve and deliver different discrete, perceptibly-renderable variations to the users during the interactive sessions, according to the experimental design rules;

automatically delivering the different discrete, perceptibly-renderable variations to users over a data network, based on the interactions of the allocator module with the programmed experiment engine.

27. A method according to claim 26, wherein the rules which govern the delivery of the variations to users are situation specific rules, including experiment rules, prediction rules or user-defined rules.

28. A method according to claim 26, wherein users are sampled at a user interface of a user during an experiment to determine which users will be assigned to receive experimental content and which will be used as experimental controls.

29. A method according to claim 28, wherein the system implements statistical sampling procedures to deliver the different variations to respective users.

30. A method according to claim 26, wherein the system conducts different experiments at the same time to increase the likelihood of achieving the predetermined outcome.

31. A method according to claim 26, wherein the system conducts different experiments over different user interfaces of users to increase the likelihood of achieving the predetermined outcome.

32. A method according to claim 26, wherein the degree to which the variations influence the behavior of users is identified.

33. A method according to claim 32, wherein one or more behavioral models are created to provide abstract descriptions of observed user behavior based on recorded actions in response to variations.

34. A method according to claim 33, wherein the behavioral models are automatically converted into predictive models that predict the likelihood of future actions by users in response to variations.

35. A method according to claim 34, wherein the predictive models are used to determine a variation for achieving the predetermined outcome, and recommends that variation for delivery to users.

36. A method according to claim 35, wherein the recommended variation is delivered.

37. A method according to claim 34, wherein a variation is automatically modified using the predictive models, to influence the likelihood of achieving the predetermined outcome when a future user is presented with that modified variation.

38. A method according to claim 34, wherein the system dynamically segments users into a plurality of segments each of which comprises users with similar behavioral characteristics.

39. A method according to claim 38, wherein data about users is collected from extrinsic databases and stored.

40. A method according to claim 38, wherein prediction rules are also generated for targeting specific variations to particular segments.

41. A method according to claim 26, wherein the entire system is automatically operated by using the recorded information to generate variations, rules governing the systematic variation of the content elements, and rules governing the delivery of the variations to users, and thereby generate new experiments.

42. A method according to claim 41, wherein new experiments are generated by determining the number of content elements in each variation, the specific variations that will be delivered during the experiments, and the number of deliveries of the variations that will be made to users.

43. A method according to claim 26, wherein all the steps are repeated to iteratively improve the information to relate the variations to the likelihood of the predetermined outcome more accurately.

44. A machine readable medium for managing delivery of digital content to users during interactive sessions between a computer system and users, the medium including a set of instructions for:

a programmed experiment engine to hold or generate experimental design rules governing the composition of combinations of digital content elements to form a variation, the content elements in a memory of a content store;

a programmed allocator module to communicate with the programmed experiment engine, to automatically interact with the programmed experiment engine to retrieve and deliver different discrete, perceptibly-renderable digital variations to the users during interactive sessions with the users, according to the experimental design rules;

automatically delivering the different discrete, perceptibly-renderable digital variations to users during the interactive sessions, based on the interactions of the allocator module with the programmed experiment engine.

45. The machine readable medium of claim 44, wherein the rules which govern the delivery of the variations to users are situation specific rules, including experiment rules, prediction rules or user-defined rules.

46. The machine readable medium of claim 44, wherein the allocator module samples users at user interface of the users during an experiment and determines which users will be assigned to receive experimental content and which will be used as experimental controls.

48. The machine readable medium of claim 44, wherein the system conducts different experiments at the same time to increase the likelihood of achieving the predetermined outcome.

49. The machine readable medium of claim 44, wherein the system conducts different experiments over different user interfaces to increase the likelihood of achieving the predetermined outcome.

50. The machine readable medium of claim 44, further comprising a set of instructions forwherein a model engine to identify the degree to which the variations influence the behavior of users.

59. The machine readable medium of claim 44, further comprising a set of instructions for a scripting/scheduling engine to automate the operation of the entire system by using the recorded information to generate new content variations, new rules governing the systematic variation of the content elements, and new rules governing the delivery of the variations to users.

60. The machine readable medium of claim 59, wherein the experiment engine generates new experiments by determining the number of content elements and the specific variations that will be delivered during the experiments, and the number of deliveries of the variations that will be made to users.

61. The machine readable medium of claim 44, wherein all the steps are repeated to iteratively improve the information to relate the variations to the likelihood of the predetermined outcome more accurately.

47. The machine readable medium of 46, wherein the system implements statistical sampling procedures to deliver the different variations to respective users.

51. The machine readable medium of 50, wherein the model engine creates one or more behavioral models which provide abstract descriptions of observed user behavior based on recorded actions in response to variations.

52. The machine readable medium of claim 51, further comprising a set of instructions for a prediction engine to automatically convert the behavioral models into predictive models that predict the likelihood of future actions by users in response to variations.

53. The machine readable medium of claim 52, wherein the prediction engine uses the predictive models to determine a variation for achieving the predetermined outcome, and recommends that variation for delivery to users.

55. The machine readable medium of claim 52, wherein the prediction engine automatically modifies a content item using the predictive models, to influence the likelihood of achieving the predetermined outcome when a future user is presented with that variation by the allocator module.

56. The machine readable medium of claim 52, wherein the system dynamically segments users into a plurality of segments each of which comprises users with similar behavioral characteristics.

57. The machine readable medium of claim 56, wherein the content store collects and holds data about users from extrinsic databases.

58. The machine readable medium of claim 56, wherein the prediction engine also generates prediction rules for targeting specific variations to particular segments.

54. The machine readable medium of 53, wherein the allocation module delivers the recommended variation.

62. A computer system for automatically managing delivery of content to users during interactive sessions between the system and users, the computer system comprising:

a computer memory content store to hold a set of digital content elements;

means for holding or generating experimental design rules governing the composition of combinations of the digital content elements to form a variation;

means for automatically retrieving different discrete, perceptibly-renderable digital variations according to the experimental design rules; and

means for automatically delivering the retrieved variations to users.

63. An automated system for delivery of content, comprising;

means for creating a model of behavior based on data collected from experiments conducted using digital content variations comprising discrete digital content elements that were automatically generated according to experimental design rules governing the composition and delivery of variations to users over a data network;

means for using the model to generate predictions of how a user will react to a particular digital variation; and

means for automatically allocating over a data network a discrete, perceptibly-renderable digital content variation to a user in accordance with a prediction.

64. An automated method for delivery of content, comprising;

creating a model of behavior based on data collected from experiments conducted using digital content variations comprising discrete content elements that were automatically generated according to experimental design rules governing the composition and delivery of variations to users over a data network;

using the model to generate predictions of how a user will react to a particular digital variation; and

automatically allocating over a data network a discrete, perceptibly-renderable digital content variation to a user in accordance with a prediction.

65. A machine readable medium comprising a set of instructions for:

creating a model of behavior based on data collected from experiments conducted using content variations comprising discrete digital content elements that were automatically generated according to experimental design rules governing the composition and delivery of variations to users over a data network;

using the model to generate predictions of how a user will react to a particular digital variation; and

automatically allocating over a data network a discrete, perceptibly-renderable digital content variation to a user in accordance with a prediction.