Interaction prediction system and method

• US 6,871,194 B1
• Filed: 07/13/2000
• Issued: 03/22/2005
• Est. Priority Date: 07/13/1999
• Status: Expired due to Fees

• Current Assignee: Sg Gaming, Inc. (Scientific Games Corporation)
• Original Assignee: Compudigm International Ltd.
• Inventors: Cardno, Andrew John
• Primary Examiner(s): Knight, Anthony
• Assistant Examiner(s): Holmes, Michael B.
• Application Number:
  US09/674,468
• Time in Patent Office: 1,713 Days
• Field of Search: 706 15- 21
• US Class Current: 706/21
• CPC Class Codes: G06Q 30/02 Marketing; Price estimation or determination; Fundraising

Abstract

The invention provides an interaction prediction system comprising a memory in which is maintained a neural network trained on data retrieved from an interaction database of interaction data representing interactions between customers and merchants, retrieval means arranged to activate the neural network and to retrieve prediction data representing future interactions between customers and merchants, and display means arranged to display a representation of the prediction data. The invention also provides a neural network training system in which a neural network is arranged to receive input data representing the data retrieved from the interaction database and to output prediction data representing interaction data predicted by the neural network. The invention also provides computer programs and methods of interaction prediction and neural network training respectively.

Claims

1. An interaction prediction system comprising:

a memory in which is maintained a neural network trained on data retrieved from an interaction database of interaction data representing interactions between customers and gaming machines, the interaction data including at least one gaming machine identifier, and at least one monetary value for the interaction;

a retrieval component arranged to activate the neural network and to retrieve prediction data representing predicted revenue from future interactions between customers and individual gaming machines; and

a display arranged to display a representation of the prediction data.

2. An interaction prediction system as claimed in claim 1 wherein the interaction data includes the date and/or time of the interaction and wherein the neural network is trained on data including the date and/or time of the interaction.

3. An interaction prediction system as claimed in claim 1 wherein the interaction data includes the spatial position of the machine involved in the interaction and wherein the neural network is trained on data including the spatial position of the machine involved in the interaction.

4. An interaction prediction system as claimed in claim 3 wherein the neural network is trained on data including the machine identifier and/or spatial position of machines neighboring the machine involved in the interactions.

5. A neural network training system comprising:

a memory in which is maintained an interaction database of interaction data representing interactions between customers and gaming machines, the interaction data including at least one gaming machine identifier and at least one monetary value for the interaction;

a retrieval component arranged to retrieve from the interaction database data representing interactions between customers and gaming machines;

a neural network arranged to receive input data representing the data retrieved from the interaction database and to output prediction data representing predicted revenue from future interactions between customers and individual gaming machines predicted by the neural network; and

a training component arranged to compare the data retrieved from the interaction database and the prediction data and to adjust the neural network based on the comparison.

6. A neural network training system as claimed in claim 5 wherein the interaction data includes the date and/or time of the interaction, the neural network further arranged to receive as input the date and/or time of interactions between customers and merchants.

7. A neural network training system as claimed in claim 5 wherein the interaction data includes the spatial position of the machine involved in the interaction and wherein the neural network is further arranged to receive as input the spatial position of the machine involved in the interaction.

8. A neural network training system as claimed in claim 7 wherein the neural network is arranged to receive as input the machine identifier and/or spatial position of machines neighboring the machine involved in the interactions.

9. An interaction prediction computer program comprising:

a neural network maintained in a memory, the neural network trained on data retrieved from an interaction database of interaction data representing interactions between customers and gaming machines, the interaction data including at least one gaming machine identifier and at least one monetary value for the interaction;

a retrieval component configured to activate the neural network, to retrieve prediction data representing predicted revenue from future interactions between customers and individual gaming machines, and to display a representation of the prediction data.

10. A computer program as claimed in claim 9 wherein the interaction data includes the date and/or time of the interaction and wherein the neural network is trained on data including the date and/or time of the interaction.

11. A computer program as claimed in claim 9 wherein the interaction data includes the spatial position of the machine involved in the interaction and wherein the neural network is trained on data including the spatial position of the machine involved in the interaction.

12. A computer program as claimed in claim 11 wherein the neural network is trained on data including the machine identifier and/or spatial position of machines neighboring the machine involved in the interactions.

13. A computer program as claimed in claim 9 embodied on a computer readable medium.

14. A neural network training computer program comprising:

an interaction database of interaction data representing interactions between customers and gaming machines, the interaction data including at least one gaming machine identifier, and at least one monetary value for the interaction;

a retrieval component configured to retrieve from the interaction database data representing interactions between customers and gaming machines;

a neural network maintained in a memory, the neural network configured to receive input data representing the data retrieved from the interaction database and to output prediction data representing predicted revenue from future interactions between customers and individual gaming machines predicted by the neural network, and

a training component configured to compare the data retrieved from the interaction database and the prediction data and to adjust the neural network based on the comparison.

15. A computer program as claimed in claim 14 wherein the interaction data includes the date and/or time of the interaction, the neural network further configured to receive as input the date and/or time of interactions between customers and merchants.

16. A computer program as claimed in claim 14 wherein the interaction data includes the spatial position of the machine involved in the interaction and wherein the neural network is further configured to receive as input the spatial position of the machine involved in the interaction.

17. A computer program as claimed in claim 16 wherein the neural network is arranged to receive as input the machine identifier and/or spatial position of machines neighboring the machine involved in the interactions.

18. A computer program as claimed in claim 14 embodied on a computer readable medium.

19. A method of predicting interactions between customers and merchants, the method comprising the steps of:

maintaining in a memory a neural network trained on data retrieved from an interaction database of interaction data representing interactions between customers and gaming machines, the interaction data including at least one gaming machine identifier and at least one monetary value for the interaction;

activating the neural network;

retrieving prediction data representing predicted revenue from future interactions between customers and individual gaming machines from the neural network; and

displaying a representation of the prediction data.

20. A method as claimed in claim 19 wherein the interaction data includes the date and/or time of the interaction and wherein the neural network is trained on data including the date and/or time of the interaction.

21. A method as claimed in claim 19 wherein the interaction data includes the spatial position of the machine involved in the interaction and wherein the neural network is trained on data including the spatial position of the machine involved in the interaction.

22. A method as claimed in claim 21 wherein the neural network is trained on data including the machine identifier and/or spatial position of machines neighboring the machine involved in the interactions.

23. A method of training a neural network comprising the steps of:

maintaining in a memory an interaction database of interaction data representing interactions between customers and gaming machines, the interaction data including at least one gaming machine identifier and at least one monetary value for the interaction;

retrieving from the interaction database data representing interactions between customers and gaming machines;

configuring a neural network to receive input data representing the data retrieved from the interaction database and to output prediction data representing predicted revenue from future interactions between customers and individual gaming machines predicted by the neural network; and

comparing the data retrieved from the interaction database and the prediction data and adjusting the neural network based on the comparison.

24. A method as claimed in claim 23 wherein the interaction data includes the date and/or time of the interaction, the neural network further configured to receive as input the date and/or time of interactions between customers and merchants.

25. A method as claimed in claim 23 wherein the interaction data includes the spatial position of the machine involved in the interaction and wherein the neural network is further configured to receive as input the spatial position of the machine involved in the interaction.

26. A method as claimed in claim 25 wherein the neural network is arranged to receive as input the machine identifier and/or spatial position of machines neighboring the machine involved in the interactions.

27. A neural network trained by the method as claimed in claim 23.