Predicting whether a party will purchase a product

• US 10,416,978 B2
• Filed: 08/08/2017
• Issued: 09/17/2019
• Est. Priority Date: 02/20/2013
• Status: Active Grant

• Current Assignee: Ivanti, Inc. (Ivanti Software, Inc.)
• Original Assignee: Ivanti, Inc. (Ivanti Software, Inc.)
• Inventors: Lehner, Brandon
• Primary Examiner(s): Singh, Gurkanwaljit
• Application Number:
  US15/671,645
• Publication Number:
  US 20180081662A1
• Time in Patent Office: 770 Days
• Field of Search: None
• CPC Class Codes: G06F 3/01 Input arrangements or combined input and output arrangements for interaction between user and computer G06F3/16 takes precedence
• CPC Class Codes: G06F 8/61 Installation
• CPC Class Codes: G06F 9/445 Program loading or initiating bootstrapping G06F9/4401; security arrangements for program loading or initiating G06F21/57
• CPC Class Codes: G06F 9/452 Remote windowing, e.g. X-Window System, desktop virtualisation protocols for virtual reality H04L67/131
• CPC Class Codes: G06Q 30/0202 Market predictions or forecasting for commercial activities

Abstract

A method for predicting whether a party will purchase a product. The method includes accessing data wherein the data is obtained from a plurality of computing environments of a plurality of parties, analyzing the data; and predicting whether one of the plurality of parties will purchase a product based on the analyzed data.

Claims

1. A system, comprising:

a memory; and

a processor associated with a cloud environment and operatively coupled to the memory, the processor configured to;

send an scan utility to a set of compute devices having access to a plurality of computing environments associated with a plurality of parties, such that each compute device from the set of compute devices stores an executable associated with the scan utility in a temporary storage of that compute device and executes the executable to collect data associated with a set of computing environments from the plurality of computing environments, each computing environment from the plurality of computing environments including a set of machines, a set of applications, and a set of networks;

receive the data from the set of compute devices;

analyze the data using a machine learning model to determine, for each party from the plurality of parties, a value for a parameter;

associate each party from the plurality of parties, based on the value for the parameter for that party, with at least one other party from the plurality of parties to produce a plurality of clusters, each cluster from the plurality of clusters including a set of parties from the plurality of parties having the value for the parameter for that party that differs less than a predefined degree from the value for the parameter for any other party in that cluster; and

determine, based on revenue generation information associated with a subset of parties from a set of parties included in a cluster from the plurality of clusters, a prediction of an amount of revenue generation of a party in the set of parties and not in the subset of parties.

2. The system of claim 1, wherein the cloud environment is associated with a vendor that provides a product, and the plurality of parties includes a customer of the product.

3. The system of claim 1, wherein the machine learning model is a neural network model.

4. The system of claim 1, wherein the parameter indicates at least one of:

a number of machines from a set of machines in a computing environment from the plurality of computing environments and associated with a party from the plurality of parties, a number of hypervisors on a set of networks in a computing environment from the plurality of computing environments and associated with a party from the plurality of parties, or a number of users associated with a set of machines in a computing environment from the plurality of computing environments and associated with a party from the plurality of parties.

5. The system of claim 1, wherein the subset of parties is a first subset of parties, and the processor is further configured to determine, based on information indicating upsell behavior of a second subset of parties from the set of parties included in the cluster, a likelihood that a party in the set of parties and not in the second subset of parties will accept an upsell offer.

6. The system of claim 1, wherein the subset of parties is a first subset of parties, and the processor is further configured to:

determine, for each party in the set of parties included in the cluster and not in a second subset of parties from the set of parties, a likelihood that that party will accept an upsell offer based on information indicating upsell behavior of the second subset of parties;

identify a party in the set of parties and not in the second subset of parties having the likelihood that that party will accept the upsell offer greater than the likelihood that other parties in the set of parties and not in the second subset of parties will accept the upsell offer; and

send a message to the party in the set of parties and not in the second subset of parties having the likelihood greater than the likelihood of the other parties in the set of parties and not in the second subset of parties, the message including information associated with the upsell offer.

7. The system of claim 1, wherein the subset of parties is a first subset of parties, and the processor is further configured to determine, based on information indicating product purchase behavior of a second subset of parties from the set of parties included in the cluster, a likelihood that a party in the set of parties and not in the second subset of parties will purchase a product.

8. The system of claim 1, wherein the subset of parties is a first subset of parties, and the processor is further configured to:

determine, for each party in the set of parties included in the cluster and not in a second subset of parties from the set of parties, a likelihood that that party will purchase a product based on information indicating product purchase behavior of the second subset of parties;

identify a party in the set of parties and not in the second subset of parties having the likelihood that that party will purchase the product greater than the likelihood that other parties in the set of parties and not in the second subset of parties will purchase the product; and

send a message to the party in the set of parties and not in the second subset of parties having the likelihood greater than the likelihood of the other parties in the set of parties and not in the second subset of parties, the message including information associated with the product.

9. A non-transitory processor-readable medium storing code representing instructions to be executed by a processor, the code comprising code to cause the processor to:

send a scan utility to a set of compute devices having access to a plurality of computing environments associated with a plurality of parties such that each compute device from the set of compute devices, in response to receiving the scan utility, installs the scan utility to collect data associated with a set of computing environments from the plurality of computing environments, each computing environment from the plurality of computing environments including a set of machines, a set of applications, and a set of networks;

receive the data from the set of compute devices;

analyze the data using a machine learning model to determine, for each party from the plurality of parties, a value for a parameter;

associate each party from the plurality of parties, based on the value for the parameter for that party, with at least one other party from the plurality of parties to produce a plurality of clusters, each cluster from the plurality of clusters including a set of parties from the plurality of parties having the value for the parameter for that party that differs less than a predefined degree from the value for the parameter for any other party in that cluster;

calculate, for a cluster from the plurality of clusters, an average amount of revenue generation of a subset of parties from the set of parties included in the cluster; and

determine, based on the average amount of revenue generation calculated for the cluster, a prediction of an amount of revenue generation of a party in the set of parties and not in the subset of parties.

10. The non-transitory processor-readable medium of claim 9, wherein the processor is associated with a cloud environment, the cloud environment is associated with a vendor that provides a product, and the plurality of parties includes a customer of the product.

11. The non-transitory processor-readable medium of claim 9, wherein the machine learning model is a neural network model.

12. The non-transitory processor-readable medium of claim 9, wherein the parameter indicates at least one of:

a number of machines from a set of machines in a computing environment from the plurality of computing environments and associated with a party from the plurality of parties, a number of hypervisors on a set of networks in a computing environment from the plurality of computing environments and associated with a party from the plurality of parties, or a number of users associated with a set of machines in a computing environment from the plurality of computing environments and associated with a party from the plurality of parties.

13. The non-transitory processor-readable medium of claim 9, wherein the subset of parties is a first subset of parties, and the code further comprises code to cause the processor to determine, based on information indicating upsell behavior of a second subset of parties from the set of parties included in the cluster, a likelihood that a party in the set of parties and not in the second subset of parties will accept an upsell offer.

14. The non-transitory processor-readable medium of claim 9, wherein the subset of parties is a first subset of parties, and the code further comprises code to cause the processor to determine, based on information indicating product purchase behavior of a second subset of parties from the set of parties included in the cluster, a likelihood that a party in the set of parties and not in the second subset of parties will purchase a product.

15. A method, comprising:

sending, from a processor associated with a cloud environment, a scan utility to a set of compute devices having access to a plurality of computing environments associated with a plurality of parties, each computing environment from the plurality of computing environments including a set of machines, a set of applications, and a set of networks, each compute device from the set of compute devices configured to execute an executable associated with the scan utility to collect data associated with a set of computing environments from the plurality of computing environments;

receiving, at the processor, the data from the set of compute devices;

analyzing, by the processor, the data using a machine learning model to determine, for each party from the plurality of parties, a value for a parameter;

associating, by the processor, a party, based on the value for the parameter for the party, with at least one other party from the plurality of parties to produce a cluster, the cluster including a set of parties from the plurality of parties having the value for the parameter for that party that differs less than a predefined degree from the value for the parameter for any other party in the cluster; and

determining, by the processor, based on revenue generation information associated with a subset of parties not including the party and from the set of parties included in the cluster, a prediction of an amount of revenue generation of the party.

16. The method of claim 15, wherein the cloud environment is associated with a vendor that provides a product, the plurality of parties includes a customer of the product, and the party is not a customer of the product.

17. The method of claim 15, wherein the subset of parties is a first subset of parties, the method further comprising:

determining, based on information indicating upsell behavior of a second subset of parties not including the party and from the set of parties included in the cluster, a likelihood that the party will accept an upsell offer.

18. The method of claim 15, wherein the subset of parties is a first subset of parties, the method further comprising:

determining, based on information indicating product purchase behavior of a second subset of parties not including the party and from the set of parties included in the cluster, a likelihood that the party will purchase a product.

19. The method of claim 15, wherein the subset of parties is a first subset of parties, the method further comprising:

determining, based on information indicating product purchase behavior of a second subset of parties not including the party and from the set of parties included in the cluster, a likelihood that the party will purchase a product; and

sending, when the likelihood meets a criterion, a message including information associated with the product to the party.

20. The method of claim 15, further comprising sending a message to a vendor associated with the cloud environment, the message including the prediction of the amount of revenue generation.