Predictive analytic modeling platform

• US 8,438,122 B1
• Filed: 05/14/2010
• Issued: 05/07/2013
• Est. Priority Date: 05/14/2010
• Status: Active Grant

• Current Assignee: Google LLC (Alphabet Inc.)
• Original Assignee: Google Inc. (Alphabet Inc.)
• Inventors: Mann, Gideon S., Lin, Wei-Hao, Breckenridge, Jordan M.
• Primary Examiner(s): Holmes, Michael B
• Application Number:
  US12/780,751
• Time in Patent Office: 1,089 Days
• Field of Search: 706/12
• US Class Current: 706/12
• CPC Class Codes: G06N 20/00 Machine learning

Abstract

Methods, systems, and apparatus, including computer programs encoded on one or more computer storage devices, for training a predictive model. In one aspect, a method includes receiving over a network predictive modeling training data from a client computing system. The training data and multiple training functions obtained from a repository of training functions are used to train multiple predictive models. A score is generated for each of the trained predictive models, where each score represents an estimation of the effectiveness of the respective trained predictive model. A first trained predictive model is selected from among the trained predictive models based on the generated scores. Access to the first trained predictive model is provided to the client computing system.

Claims

1. A computer-implemented system comprising:

one or more computers;

one or more data storage devices coupled to the one or more computers;

the one or more data storage devices storing;

a repository of training functions;

a repository of trained predictive models; and

instructions that, when executed by the one or more computers, cause the one or more computers to perform operations comprising;

receiving over a network a plurality of sets of predictive modeling training data from a first plurality of client computing systems;

for each set of plurality of sets of predictive modeling training data;

using the training data and a plurality of training functions obtained from the repository to train a plurality of predictive models;

generating a score for each of the plurality of trained predictive models, where each score represents an estimation of the effectiveness of the respective trained predictive model; and

selecting a trained predictive model from among the plurality of trained predictive models based on the generated scores;

wherein a plurality of trained predictive models are thereby generated and selected;

storing the plurality of selected trained predictive models in the repository of trained predictive models; and

providing access to the plurality of trained predictive models to a second plurality of client computing systems.

2. The system of claim 1, wherein the operations further comprise:

receiving data from a first client computing system included in the first plurality of client computing systems indicating that permission is granted to a second client computing system included in the second plurality of client computing systems for the second client computing system to access the trained predictive model that was trained using training data received from the first client computing system.

3. The system of claim 1, wherein providing access to the plurality of trained predictive models includes providing a web page accessible by the second plurality of client computing systems that is configured for the second plurality of client computing systems to browse the repository of trained predictive models that are available for use by the second plurality of client computing systems.

4. The system of claim 1, wherein providing access to the plurality of trained predictive models includes providing a catalogue that includes descriptions of types of input data received by each trained predictive model included in the repository of trained predictive models and types of predictive output generated in response by the respective trained predictive models.

5. The system of claim 1, wherein the operations further comprise:

receiving input data and a request for a predictive output from a particular client computing system that is included in the second plurality of client computing systems;

generating the predictive output using a first trained predictive model from the repository of trained predictive models; and

providing the predictive output to the particular client computing system.

6. The system of claim 1, wherein the operations further comprise:

receiving input data and a request for a predictive output from a particular client computing system that is included in the second plurality of client computing systems;

generating the predictive output using a first trained predictive model from the repository of trained predictive models and a second trained predictive model from the repository of trained predictive models;

providing the predictive output to the particular client computing system;

apportioning a fee received from the particular client computing system to generate the predictive output to a first client computing system and to a second client computing system from the first plurality of client computing systems, wherein the first client computing system provided a first set of training data that was used to train the first trained predictive model and the second client computing system provided a second set of training data that was used to trained the second trained predictive model.

7. A computer-implemented method comprising:

receiving over a network a plurality of sets of predictive modeling training data from a first plurality of client computing systems;

for each set of plurality of sets of predictive modeling training data;

using the training data and a plurality of training functions to train a plurality of predictive models;

generating a score for each of the plurality of trained predictive models, where each score represents an estimation of the effectiveness of the respective trained predictive model; and

selecting a trained predictive model from among the plurality of trained predictive models based on the generated scores;

wherein a plurality of trained predictive models are thereby generated and selected;

storing the plurality of selected trained predictive models in a repository of trained predictive models; and

providing access to the plurality of trained predictive models to a second plurality of client computing systems.

8. The method of claim 7, further comprising:

receiving data from a first client computing system included in the first plurality of client computing systems indicating that permission is granted to a second client computing system included in the second plurality of client computing systems for the second client computing system to access the trained predictive model that was trained using training data received from the first client computing system.

9. The method of claim 7, wherein providing access to the plurality of trained predictive models includes providing a web page accessible by the second plurality of client computing systems that is configured for the second plurality of client computing systems to browse the repository of trained predictive models that are available for use by the second plurality of client computing systems.

10. The method of claim 7, wherein providing access to the plurality of trained predictive models includes providing a catalogue that includes descriptions of types of input data received by each trained predictive model included in the repository of trained predictive models and types of predictive output generated in response by the respective trained predictive models.

11. The method of claim 7, further comprising:

receiving input data and a request for a predictive output from a particular client computing system that is included in the second plurality of client computing systems;

generating the predictive output using a first trained predictive model from the repository of trained predictive models; and

providing the predictive output to the particular client computing system.

12. The method of claim 7, further comprising:

receiving input data and a request for a predictive output from a particular client computing system that is included in the second plurality of client computing systems;

generating the predictive output using a first trained predictive model from the repository of trained predictive models and a second trained predictive model from the repository of trained predictive models;

providing the predictive output to the particular client computing system;

apportioning a fee received from the particular client computing system to generate the predictive output to a first client computing system and to a second client computing system from the first plurality of client computing systems, wherein the first client computing system provided a first set of training data that was used to train the first trained predictive model and the second client computing system provided a second set of training data that was used to trained the second trained predictive model.

13. A non-transitory computer-readable storage device encoded with a computer program product, the computer program product comprising instructions that when executed on one or more computers cause the one or more computers to perform operations comprising:

receiving over a network a plurality of sets of predictive modeling training data from a first plurality of client computing systems;

for each set of plurality of sets of predictive modeling training data;

using the training data and a plurality of training functions to train a plurality of predictive models;

generating a score for each of the plurality of trained predictive models, where each score represents an estimation of the effectiveness of the respective trained predictive model; and

selecting a trained predictive model from among the plurality of trained predictive models based on the generated scores;

wherein a plurality of trained predictive models are thereby generated and selected;

storing the plurality of selected trained predictive models in a repository of trained predictive models; and

providing access to the plurality of trained predictive models to a second plurality of client computing systems.

14. The computer-readable storage device of claim 13, the operations further comprising:

receiving data from a first client computing system included in the first plurality of client computing systems indicating that permission is granted to a second client computing system included in the second plurality of client computing systems for the second client computing system to access the trained predictive model that was trained using training data received from the first client computing system.

15. The computer-readable storage device of claim 13, wherein providing access to the plurality of trained predictive models includes providing a web page accessible by the second plurality of client computing systems that is configured for the second plurality of client computing systems to browse the repository of trained predictive models that are available for use by the second plurality of client computing systems.

16. The computer-readable storage device of claim 13, wherein providing access to the plurality of trained predictive models includes providing a catalogue that includes descriptions of types of input data received by each trained predictive model included in the repository of trained predictive models and types of predictive output generated in response by the respective trained predictive models.

17. The computer-readable storage device of claim 13, the operations further comprising:

receiving input data and a request for a predictive output from a particular client computing system that is included in the second plurality of client computing systems;

generating the predictive output using a first trained predictive model from the repository of trained predictive models; and

providing the predictive output to the particular client computing system.

18. The computer-readable storage device of claim 13, the operations further comprising:

receiving input data and a request for a predictive output from a particular client computing system that is included in the second plurality of client computing systems;

generating the predictive output using a first trained predictive model from the repository of trained predictive models and a second trained predictive model from the repository of trained predictive models;

providing the predictive output to the particular client computing system;

apportioning a fee received from the particular client computing system to generate the predictive output to a first client computing system and to a second client computing system from the first plurality of client computing systems, wherein the first client computing system provided a first set of training data that was used to train the first trained predictive model and the second client computing system provided a second set of training data that was used to trained the second trained predictive model.