Systems and methods for clustering of customers using transaction patterns

A 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 at least one or more credit cards or debit cards;
• and
• the plurality of customers that purchased the one or more items from the e-commerce website using the at least 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, such that each e-commerce payment option of the subset of e-commerce payment options is associated with more than one of the plurality of e-commerce customer identifications;
• filtering by the back-end device, the each e-commerce payment option of the subset of e-commerce payment options as being associated with either:
• a single one of the plurality of customers with the more than one of the plurality of e-commerce customer identifications;
• or
• more than one of the plurality of customers, wherein the more than one of the plurality of customers are related to each other as part of a same household and share a same credit card or a same debit card;
• wherein the filtering comprises:
• identifying a first multiple of the plurality of e-commerce customer identifications as a same customer of the plurality of customers;
• identifying a second multiple of the plurality of e-commerce customer identifications as related customers of the plurality of customers as part of the same household and share the same credit card or the same debit card;
• and
• 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:
• cit represents an ith customer information in a record Dt,
• cjt represents a jth customer information in the record Dt,
• P(Itij cti, ctj) is a posterior probability to be calculated,
• Itij represents a binary random variable that denotes whether two customers cit and cjt in the record Dt belong to category 1(Itij=1) or otherwise,
• x represents a vector representing features derived from customer information in cit and cjt, and
• w represents weights of a logistic regression;
• determining by the back-end device, to determine similarities in the customer information and filter for similarities using a similarity score, wherein:
• searching the customer information comprising first names, last names, and physical addresses;
• applying an edit distance on the first names and the last names between all pairs of customer information in a record Dt that shared a single e-commerce payment option;
• filtering 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 second multiple of the plurality of e-commerce customer identifications;
• targeting product recommendations to each of the classifications of customers comprising the first multiple of the plurality of e-commerce customer identifications or the second multiple of the plurality of e-commerce customer identifications;
• sending the classification and the product recommendations to the first and second multiples of the plurality of e-commerce customer identifications to display at the front-end device;
• and
• providing, by the back-end device, instructions to display the classification and the product recommendations of each e-commerce customer identification of a subset of e-commerce customer identifications at the display device of the front-end device.

A system for targeting and providing recommendations to e-commerce customers, the system comprising:

• a database;
• a front-end device comprising an input device and a display device;
• and
• a back-end device comprising one or more processors and one or more non-transitory memory devices operably coupled to the one or more processors and storing executable and operational data, the executable and operational data effective to cause the one or more processors to:
• receive a query from an operator of an e-commerce web site that operates the 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;
• receive the customer information from the plurality of customers of the e-commerce website from the database, the customer information comprising:
• a plurality of e-commerce customer identifications, wherein the 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 at least one or more credit cards or debit cards;
• and
• the plurality of customers that purchased the one or more items from the e-commerce website using the at least one or more credit cards or debit cards;
• filter 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;
• filter 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 as at least one of:
• a single one of the plurality of customers with more than one of the subset of e-commerce customer identifications of the plurality of e-commerce customer identifications corresponding to the single e-commerce payment option;
• or
• more than one customer of the plurality of customers with the more than one of the subset of e-commerce customer identifications of the plurality of e-commerce customers identifications and corresponding to the single e-commerce payment option wherein more than one of the customers of the plurality of customers are related to each other as part of a same household and share a same credit card or a same debit card;
• wherein the filtering comprises:
• identify a first multiple of the subset of e-commerce customer identifications as the single one of the plurality of customers;
• or
• identify a second multiple of the subset of e-commerce customer identifications as being related customers as part of the same household and share the same credit card or the same debit card;
• wherein the filter also comprises 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:
• cit represents an ith customer information in a record Dt,
• cjt represents a jth customer information in the record Dt,
• P(Itij cti, ctj) is a posterior probability to be calculated,
• Itij cti represents a binary random variable that denotes whether two customers cit and cjt in the record Dt belong to category 1(Itij=1) or otherwise,
• x represents a vector representing features derived from customer information in cit and cjt, and
• w represents weights of a logistic regression;
• determine, using the one or more processors, to determine similarities in the customer information and filter for similarities using a similarity score, wherein:
• searching the customer information comprising first names, last names, and physical addresses;
• applying an edit distance on the first names and the last names between all pairs of customer information in a record Dt that shared the single e-commerce payment option;
• filtering the customer information by the single e-commerce payment option attributable to multiple e-commerce customer identifications and by transaction history;
• and
• when all the edit distances for the customer information falls below a preset threshold, then the customer information is grouped as a second multiple of the plurality of e-commerce customer identifications;
• send the classification to the first and second multiples of the plurality of e-commerce customer identifications to display at the front-end device;
• and
• providing 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.