Determining Groups of Individuals Based on Multiple Items of Individual Transaction Data

A method comprising the following steps:

• initializing an item category for each of multiple purchased items identified in a purchase record;
• initializing a customer segment value for each of the multiple purchased items identified in the purchase record based on one or more historical purchasing patterns;
• updating the customer segment value for each of the multiple purchased items based on (i) the customer segment values for each other purchased item identified in the purchase record and (ii) the item categories initialized for the other purchased items identified in the purchase record;
• updating the item category for each of the multiple purchased items based on (i) the customer segment values for the other purchased items identified in the purchase record and (ii) the item categories initialized for the other purchased items identified in the purchase record;
• and
• determining a customer segment composition of a group of individuals associated with the multiple purchased items identified in the purchase record based on (i) the updated customer segment values and (ii) the updated item categories;
• wherein at least one of the steps is carried out by a computing device.

A method comprising the following steps:

• initializing an item category for each of multiple purchased items identified in a purchase record;
• initializing a customer segment value for each of the multiple purchased items identified in the purchase record based on one or more historical purchasing patterns;
• updating the customer segment value for each of the multiple purchased items based on (i) a customer identifier for the purchase record, (ii) the customer segment values for each other purchased item identified in the purchase record, and (iii) the item categories initialized for the other purchased items identified in the purchase record;
• updating the item category for each of the multiple purchased items based on (i) the customer segment values for the other purchased items identified in the purchase record and (ii) the item categories initialized for the other purchased items identified in the purchase record;
• and
• determining a customer segment composition of a group of individuals associated with the multiple purchased items identified in the purchase record based on (i) the customer identifier for the purchase record, (ii) the updated customer segment values and (iii) the updated item categories;
• wherein at least one of the steps is carried out by a computing device.

A method comprising the following steps:

• initializing an item category for each of multiple purchased items identified in a purchase record;
• initializing a customer identifier for the purchase record;
• determining a network of additional customers associated with the customer identifier initialized for the purchase record based on one or more parameters;
• generating a distribution estimate over multiple customer segments for multiple item categories across multiple additional purchase records for the customer identifier by randomly sampling one or more of the additional customers in the network;
• and
• determining a customer segment composition of a group of individuals associated with the customer identifier based on (i) the purchase record and (ii) the distribution estimate;
• wherein at least one of the steps is carried out by a computing device.