Method and system for generating predictive models for scoring and prioritizing leads

Patent metadata

Field	Value
Publication number	US-10706359-B2
Application number	US-201715405076-A
Country	US
Kind code	B2
Filing date	Jan 12, 2017
Priority date	Nov 30, 2012
Publication date	Jul 7, 2020
Grant date	Jul 7, 2020

Abstract

A computer implemented system for automating the generation of an analytic model includes a processor configured to process a plurality of data sets. Each data set includes values for a plurality of variables. A time-stamping module is configured to derive values for a plurality of elapsed-time variables for each data set, and the plurality of variables and plurality of elapsed-time variables are included in a plurality of model variables. A model generator is configured to create a plurality of comparison analytic models each based on a different subset of model variables. Each comparison analytic model is configured to operate on new data sets associated with current leads, and to output a likelihood of successfully closing an associated transaction. A model testing module is configured to select an operational analytic model from among the comparison analytic models based on a quality metric.

First claim

What is claimed is:

1. A computer implemented system comprising:
a processor; and
a memory communicatively coupled to the processor, the memory storing:
a customer relationship management (CRM) database configured to store a first data set from a plurality of data sets, wherein the first data set comprises a plurality of variables; and
instructions that, when executed by the processor, cause the processor to perform operations comprising:
identifying a first time variable for the first data set and a second time variable for the first data set;
calculating a difference between the first time variable and the second time variable to produce an elapsed time associated with the first data set;
adding the elapsed time to the plurality of variables of the CRM database;
extracting a keyword from the first data set;
assigning a weight to the keyword to produce structured data for the first data set;
adding the structured data to the plurality of variables of the CRM database;
creating a first comparison analytic model for the first data set using the plurality of variables, wherein the first comparison analytic model is associated with a first model type, and wherein the first comparison analytic model is configured to operate on a new data set associated with a first sales lead; and
outputting a first representation of a first likelihood of successfully closing a first transaction associated with the first sales lead.

2. The system of claim 1 , the operations comprising:
creating a plurality of comparison analytic models for a plurality of respective model types, wherein each respective comparison analytic model is created based on a respective subset of the plurality of variables;
selecting a second comparison analytic model from the plurality of comparison analytic models associated with a second model type of the plurality of model types based on a quality metric applied to the plurality of comparison analytic models;
applying the second comparison analytic model to generate a second representation of a second likelihood of successfully closing a second transaction associated with a second sales lead; and
reporting the second representation of the second comparison analytic model for the second sales lead.

3. The system of claim 2 , the operations comprising:
applying a third comparison analytic model of the plurality of comparison analytic models to the new data set associated on an ongoing basis to generate third representations of a third likelihood of successfully closing a third transaction associated with a third sales lead; and
storing, in the memory, the generated third representations of the third comparison analytic model.

4. The system of claim 3 , the operations comprising:
receiving an updated data set indicating an actual result of the second transaction; and
evaluating a predictive performance of the second comparison analytic model based on the updated data set.

5. The system of claim 4 , the operations comprising:
selecting the third comparison analytic model from among the plurality of comparison analytic models based on the evaluated predictive performance of the second comparison analytic model.

6. The system of claim 4 , the operations comprising:
regenerating the second comparison analytic model, based at least in part on the updated data sets, in response to the predictive performance of the second comparison analytic model being less than a threshold value.

7. The system of claim 6 , the operations comprising:
regenerating the second comparison analytic model in a stateful manner.

8. The system of claim 6 , the operations comprising:
regenerating the second comparison analytic model in a stateless manner.

9. The system of claim 1 , wherein the first representation of the first likelihood of successfully closing the first transaction associated with the first sales lead comprises: (i) a score indicating a relative likelihood that the first sales lead will lead to successful closure of the transaction, (ii) a prioritized ranking of the first sales lead to a plurality of first sales leads based on the respective likelihood that the first sales lead will result in successful closure of the transaction, or a combination thereof.

10. The system of claim 1 , the operations comprising:
adding at least one additional variable to the plurality of variables; and
derive a value for the at least one additional variable by converting unstructured data associated with at least one data set into structured data associated with the respective data set.

11. A method comprising:
identifying a first time variable for a first data set and a second time variable for the first data set;
calculating a difference between the first time variable and the second time variable to produce an elapsed time associated with the first data set;
adding the elapsed time to a plurality of variables of a customer relationship management (CRM) database;
extracting a keyword from the first data set;
assigning a weight to the keyword to produce structured data for the first data set;
adding the structured data to the plurality of variables of the CRM database;
creating a first comparison analytic model for the first data set using the plurality of variables, wherein the first comparison analytic model is associated with a first model type, and wherein the first comparison analytic model is configured to operate on a new data set associated with a first sales lead; and
outputting a first representation of a first likelihood of successfully closing a first transaction associated with the first sales lead.

12. The method of claim 11 , comprising:
creating a plurality of comparison analytic models for a plurality of respective model types, wherein each respective comparison analytic model is created based on a respective subset of the plurality of variables;
selecting a second comparison analytic model from the plurality of comparison analytic models associated with a second model type of the plurality of model types based on a quality metric applied to the plurality of comparison analytic models;
applying the second comparison analytic model to generate a second representation of a second likelihood of successfully closing a second transaction associated with a second sales lead; and
reporting the second representation of the second comparison analytic model for the second sales lead.

13. The method of claim 12 , comprising:
applying a third comparison analytic model of the plurality of comparison analytic models to the new data set associated on an ongoing basis to generate third representations of a third likelihood of successfully closing a third transaction associated with a third sales lead; and
storing the resulting generated third representations of the third comparison analytic model.

14. The method of claim 13 , comprising:
receiving an updated data set indicating an actual result of the second transaction; and
evaluating a predictive performance of the second comparison analytic model based on the updated data set.

15. The method of claim 14 , comprising:
selecting the third comparison analytic model from among the plurality of comparison analytic models based on the evaluated predictive performance of the second comparison analytic model.

16. The method of claim 14 , comprising:
regenerating the second comparison analytic model, based at least in part on the updated data sets, in response to the predictive performance of the second comparison analytic model being less than a threshold value.

17. The method of claim

Assignees

• Servicenow Inc

Inventors

• Jayaraman Baskar
• Chatterjee Debashish
• Govindarajan Kannan
• Rajan Ganesh

Classifications

• G06N5/02 Primary

  Knowledge representation; Symbolic representation · CPC title

• G06F16/22

  Indexing; Data structures therefor; Storage structures · CPC title

• G06N20/00

  Machine learning · CPC title