Contact recommendations based on purchase history

• US 10,354,264 B2
• Filed: 09/15/2014
• Issued: 07/16/2019
• Est. Priority Date: 03/24/2014
• Status: Active Grant

• Current Assignee: Salesforce.com, Inc.
• Original Assignee: Salesforce.com, Inc.
• Inventors: Jagota, Arun, Haardt, Gregory, Ramachandran, Govardana Sachithanandam, Ming, Lei, Fuchs, Matthew, Vitchev, George, Wong, Fang
• Primary Examiner(s): Yesildag, Mehmet
• Assistant Examiner(s): Byrd, Uche
• Application Number:
  US14/486,111
• Publication Number:
  US 20150269595A1
• Time in Patent Office: 1,765 Days
• CPC Class Codes: G06Q 10/06315 Needs-based resource requirements planning or analysis
• CPC Class Codes: G06Q 10/067 Enterprise or organisation modelling
• CPC Class Codes: G06Q 10/103 Workflow collaboration or project management
• CPC Class Codes: G06Q 10/105 Human resources
• CPC Class Codes: G06Q 30/00 Commerce
• CPC Class Codes: G06Q 30/02 Marketing; Price estimation or determination; Fundraising
• CPC Class Codes: G06Q 30/0202 Market predictions or forecasting for commercial activities
• CPC Class Codes: G06Q 30/0235 constrained by time limit or expiration date
• CPC Class Codes: G06Q 30/0255 based on user history
• CPC Class Codes: G06Q 30/06 Buying, selling or leasing transactions
• CPC Class Codes: G06Q 30/0631 Item recommendations
• CPC Class Codes: G06Q 40/00 Finance; Insurance; Tax strategies; Processing of corporate or income taxes

Abstract

Contact recommendations based on purchase history are described. A system creates a directed graph of nodes in which at least some of the nodes are connected by directed arcs, wherein a directed arc from a first node to a second node represents a conditional probability that previous users who purchased a first contact also purchased a second contact. The system identifies a set of contacts purchased by a current user. The system estimates a prospective purchase probability based on a historical probability that previous users purchased a specific contact and a related probability that previous users who purchased the specific contact also purchased a contact in the set of contacts, for each candidate contact. The system outputs a recommendation for the current user to purchase a recommended candidate contact based on a corresponding prospective purchase probability.

Claims

1. A system for contact recommendations based on purchase history, the system comprising:

one or more processors of a computer communicatively coupled to a contact database system; and

a non-transitory computer readable medium storing a plurality of instructions, which when executed by the computer, cause the one or more processors to;

receive a request to purchase a plurality of contacts from the contact database by a current user, the request being received over a network;

create a directed graph, based on a stored plurality of historical purchase data within the contact database, of a plurality of nodes in which at least some of the plurality of nodes are connected by a plurality of directed arcs, wherein a directed arc from a first node to a second node represents a conditional probability that previous users who purchased a first contact also purchased a second contact within the stored historical purchase data, a number of outgoing directed arcs from the first node being limited to a maximum number of outgoing directed arcs, each of the maximum number of outgoing directed arcs representing a corresponding conditional probability that is greater than each non-zero conditional probability corresponding to each potential outgoing directed arc;

determine a set of candidate contacts, each candidate contact in the set of candidate contacts being connected to one of the requested plurality of contacts by a direct arc;

estimate a prospective purchase probability for each of the candidate contacts in the set of candidate contacts connected by the plurality of directed arcs based on a historical probability that previous users purchased a specific contact of the candidate contacts and a related probability that previous users who purchased the specific contact also purchased a contact in the requested plurality of contacts, the historical probability and the related probability being derived from the historical purchase data, the previous users being different than the current user;

output a recommendation for the current user to purchase a recommended candidate contact from the set of candidate contacts based on a corresponding prospective purchase probability associated with the recommended candidate contact; and

transmit the recommendation over the network to the current user.

2. The system of claim 1, wherein estimating the prospective purchase probability is further based on another related probability that previous users who purchased the specific contact also purchased another contact in the set of contacts, for each candidate contact.

3. The system of claim 1, wherein the historical probability that previous users purchased the specific contact is adjusted for purchase recency.

4. The system of claim 1, comprising further instructions, which when executed, cause the one or more processors to identify each candidate contact based on identifying a number of outgoing directed arcs from a candidate contact to contacts in the set of contacts.

5. A computer program product comprising computer-readable program code to be executed by one or more processors when retrieved from a non-transitory computer-readable medium, the program code including instructions to:

receive a request to purchase a plurality of contacts from a contact database system by a current user, the request being received over a network;

create a directed graph, based on a stored plurality of historical purchase data within the contact database, of a plurality of nodes in which at least some of the plurality of nodes are connected by a plurality of directed arcs, wherein a directed arc from a first node to a second node represents a conditional probability that previous users who purchased a first contact also purchased a second contact within the stored historical purchase data, wherein a number of outgoing directed arcs from the first node is limited to a maximum number of outgoing directed arcs, each of the maximum number of outgoing directed arcs representing a corresponding conditional probability that is greater than each non-zero conditional probability corresponding to each potential outgoing directed arc;

determine a set of candidate contacts, each candidate contact in the set of candidate contacts being connected to one of the requested plurality of contacts by a direct arc;

estimate a prospective purchase probability for each of the candidate contacts in the set of candidate contacts connected by the plurality of directed arcs based on a historical probability that previous users purchased a specific contact of the candidate contacts and a related probability that previous users who purchased the specific contact also purchased a contact in the requested plurality of contacts, the historical probability and the related probability being derived from the historical purchase data, the previous users being different than the current user;

output a recommendation for the current user to purchase a recommended candidate contact from the set of candidate contacts based on a corresponding prospective purchase probability associated with the recommended candidate contact; and

transmit the recommendation over the network to the current user.

6. The computer program product of claim 5, wherein estimating the prospective purchase probability is further based on another related probability that previous users who purchased the specific contact also purchased another contact in the set of contacts, for each candidate contact.

7. The computer program product of claim 5, wherein the historical probability that previous users purchased the specific contact is adjusted for purchase recency.

8. The computer program product of claim 5, wherein the program code comprises further instructions to identify each candidate contact based on identifying a number of outgoing directed arcs from a candidate contact to contacts in the set of contacts.

9. A method for contact recommendations based on purchase history, the method comprising:

receiving a request to purchase a plurality of contacts from a contact database system by a current user, the request being received over a network;

creating, based on a stored plurality of historical purchase data within the contact database, a directed graph of a plurality of nodes in which at least some of the plurality of nodes are connected by a plurality of directed arcs, wherein a directed arc from a first node to a second node represents a conditional probability that previous users who purchased a first contact also purchased a second contact within the stored historical purchase data, a number of outgoing directed arcs from the first node being limited to a maximum number of outgoing directed arcs, each of the maximum number of outgoing directed arcs representing a corresponding conditional probability that is greater than each non-zero conditional probability corresponding to each potential outgoing directed arc;

determine a set of candidate contacts, each candidate contact in the set of candidate contacts being connected to one of the requested plurality of contacts by a direct arc;

estimating a prospective purchase probability for each of the candidate contacts in the set of candidate contacts connected by the plurality of directed arcs based on a historical probability that previous users purchased a specific contact of the candidate contacts and a related probability that previous users who purchased the specific contact also purchased a contact in the requested plurality of contacts, the historical probability and the related probability being derived from the historical purchase data, the previous users being different than the current user;

outputting a recommendation for the current user to purchase a recommended candidate contact from the set of candidate contacts based on a corresponding prospective purchase probability associated with the recommended candidate contact; and

transmitting the recommendation over the network to the current user.

10. The method of claim 9, wherein estimating the prospective purchase probability is further based on another related probability that previous users who purchased the specific contact also purchased another contact in the set of contacts, for each candidate contact.

11. The method of claim 9, wherein the historical probability that previous users purchased the specific contact is adjusted for purchase recency.

12. The method of claim 9, the method further comprising identifying each candidate contact based on identifying a number of outgoing directed arcs from a candidate contact to contacts in the set of contacts.

13. A system comprising:

a processor-based application, which when executed on a computer communicatively coupled to a contact database, will cause the processor to;

receive a request to purchase a plurality of contacts from the contact database system by a current user, the request being received over a network;

create a directed graph, based on a stored plurality of historical purchase data within the contact database, of a plurality of nodes in which at least some of the plurality of nodes are connected by a plurality of directed arcs, wherein a directed arc from a first node to a second node represents a conditional probability that previous users who purchased a first contact also purchased a second contact within the stored historical purchase data, a number of outgoing directed arcs from the first node being limited to a maximum number of outgoing directed arcs, each of the maximum number of outgoing directed arcs representing a corresponding conditional probability that is greater than each non-zero conditional probability corresponding to each potential outgoing directed arc;

determine a set of candidate contacts, each candidate contact in the set of candidate contacts being connected to one of the requested plurality of contacts by a direct arc;

estimate a prospective purchase probability for each of the candidate contacts in the set of candidate contacts connected by the plurality of directed arcs based on a historical probability that previous users purchased a specific contact of the candidate contacts and a related probability that previous users who purchased the specific contact also purchased a contact in the requested plurality of contacts, the historical probability and the related probability being derived from the historical purchase data, the previous users being different than the current user;

output a recommendation for the current user to purchase a recommended candidate contact from the set of candidate contacts based on a corresponding prospective purchase probability associated with the recommended candidate contact; and

transmit the recommendation over the network to the current user.

14. The system of claim 13, wherein estimating the prospective purchase probability is further based on another related probability that previous users who purchased the specific contact also purchased another contact in the set of contacts, for each candidate contact.

15. The system of claim 13, wherein the historical probability that previous users purchased the specific contact is adjusted for purchase recency.

16. The system of claim 13, the method further comprising transmitting code to identify each candidate contact based on identifying a number of outgoing directed arcs from a candidate contact to contacts in the set of contacts.