Systems and methods for clustering of customers using transaction patterns

Patent metadata

Field	Value
Publication number	US-10096013-B2
Application number	US-201313905863-A
Country	US
Kind code	B2
Filing date	May 30, 2013
Priority date	May 30, 2013
Publication date	Oct 9, 2018
Grant date	Oct 9, 2018

Abstract

Example systems and methods for clustering of customers using patterns in their transactions are described. In one implementation, a method receives customer information that includes at least a plurality of customer identifications and a plurality of payment options associated with a plurality of customers. The method identifies a subset of payment options, from among the payment options, and a subset of customer identifications, from among the customer identifications, such that each payment option of the subset of payment options is associated with more than one customer identification of the subset of customer identifications. The method then classifies each customer identification of the subset of customer identifications as either of one of more than one of the customer identifications associated with a single one of the customers or one of more than one of the customer identifications associated with more than one of the customers who are related to each other.

First claim

The invention claimed is:

1. A method of identifying e-commerce customer identifications for an individual customer, or for individual customers that are related to each other or belong to a same household, for targeting recommendations to the individual customer or the individual customers, the method comprising:
receiving, by a back-end device comprising one or more processors, a query from an operator of an e-commerce website that operates a front-end device requesting a classification of customer information of a plurality of customers of the e-commerce website that have more than one e-commerce customer identification mapped to a same e-commerce payment option, the front-end device comprising an input device and a display device;
receiving, by the back-end device, the customer information from the plurality of customers of the e-commerce website from a database, the customer information comprising:
a plurality of e-commerce customer identifications, wherein each of the plurality of e-commerce customer identifications comprise at least one of a user name, a password, or an account;
a plurality of e-commerce payment options associated with one or more items purchased on the e-commerce website, wherein an e-commerce payment option of the plurality of e-commerce payment options comprises one or more credit cards or debit cards; and
the plurality of customers that purchased the one or more items from the e-commerce web site using the one or more credit cards or debit cards;

filtering by the back-end device, a subset of e-commerce payment options from among the plurality of e-commerce payment options, and a subset of e-commerce customer identifications from among the plurality of e-commerce customer identifications, such that each e-commerce payment option of the subset of e-commerce payment options is associated with the more than one e-commerce customer identification of the subset of e-commerce customer identifications;
filtering by the back-end device, each e-commerce customer identification of the subset of e-commerce customer identifications associated with a single e-commerce payment option of the subset of e-commerce payment options into two categories comprising either of:
a category one comprising an individual customer mapped to more than one of the subset of e-commerce customer identifications of the plurality of e-commerce customer identifications and corresponding to the single e-commerce payment option; or
a category two comprising more than one customer of the plurality of customers mapped to the more than one of the subset of e-commerce customer identifications of the plurality of e-commerce customer identifications and corresponding to the single e-commerce payment option wherein the more than one customer of the plurality of customers are related to each other as part of the same household and share a same credit card or debit card;

wherein filtering each e-commerce customer identification of the subset of e-commerce customer identifications associated with the single e-commerce payment option of the subset of e-commerce payment options comprises filtering the e-commerce customer identifications into the category one or the category two using probabilistic matching by a logistic regression model expressed as follows:

P
⁡

(

I
t
ij

=

1
|

c
t
i

,

c
t
j

)

=

1

1
+

e

-
wx

wherein:
c i t represents an i th customer information in a record D t ,
c i t represents a j th customer information in the record D t ,
P(I t ij c t i , c t j ) is a posterior probability to be calculated,
I t ij represents a binary random variable that denotes whether two customers c i t and c j t in the record D t belong to category 1(I t ij =1) or otherwise,
x represents a vector representing features derived from customer information in c i t and c j t , and
w represents weights of a logistic regression;

determining, by the back-end device, when the record D t cannot be classified in the category one by using the one or more processors to determine similarities in the customer information and filtering for similarities using a similarity score, wherein:
searching, with the one or more processors, the customer information comprising at least first names, last names, and physical addresses;
applying, with the one or more processors, an edit distance on the first names and the last names between all pairs of the customer information in the record D t that shared the single e-commerce payment option;
filtering, with the one or more processors, the customer information by the single e-commerce payment option attributable to multiple e-commerce customer identifications and by transaction history; and
when the edit distance for the customer information falls below a preset threshold, then the customer information is grouped as the category two;

sending the classification of each e-commerce customer identification of the subset of e-commerce customer identifications to the front-end device; and
providing, by the back-end device, instructions to display the classification of each e-commerce customer identification of the subset of e-commerce customer identifications at the display device of the front-end device.

2. The method of claim 1 , wherein:
for the each of the plurality of customers, the customer information further comprises:
an email address; and
the transaction history of items purchased on the e-commerce website.

3. The method of claim 1 , wherein:
filtering the subset of e-commerce payment options comprises:
filtering for one or more of the plurality of e-commerce payment options associated with the more than one customer of the plurality of e-commerce customer identifications.

4. The method of claim 3 , wherein:
the each of the plurality of e-commerce customer identifications have the transaction history of at least one of the one or more items purchased on the e-commerce website.

5. The method of claim 1 , wherein:
filtering each e-commerce customer identification of the subset of e-commerce customer identifications comprises:
for the each e-commerce payment option of the subset of e-commerce payment options, determining a similarity score for each of the more than one e-commerce customer identification mapped to the same e-commerce payment option, using:
let D t ={D i }, i=1, 2, . . . N, where in D i denotes a collection of information pertaining to customers who used a particular payment option t i , and N denotes a number of records in a data set; and
each record D k may be expressed as {t k , c 1 k , c 2 k , . . . } wher

Assignees

• Wal Mart Stores Inc
• Walmart Apollo Llc

Inventors

• Ali Afroza
• Achan Kannan
• Benson Ron

Classifications

• G06Q40/00

  Finance; Insurance; Tax strategies; Processing of corporate or income taxes · CPC title

• G06Q20/22 Primary

  Payment schemes or models · CPC title

• G06Q20/227

  characterised in that multiple accounts are available, e.g. to the payer · CPC title