System for individualized customer interaction

• US 8,650,075 B2
• Filed: 12/21/2011
• Issued: 02/11/2014
• Est. Priority Date: 02/27/2004
• Status: Active Grant

• Current Assignee: Accenture Global Services Limited (Accenture PLC)
• Original Assignee: Acenture Global Services Limited
• Inventors: Fano, Andrew E., Cumby, Chad M., Ghani, Rayid, Krema, Marko
• Primary Examiner(s): Hamilton, Matthew L.
• Application Number:
  US13/332,590
• Publication Number:
  US 20120123844A1
• Time in Patent Office: 783 Days
• Field of Search: 705/14, 705/26
• US Class Current: 705/14.1
• CPC Class Codes: G06N 20/00 Machine learning
• CPC Class Codes: G06N 99/00 Subject matter not provided for in other groups of this subclass
• CPC Class Codes: G06Q 10/087 Inventory or stock management, e.g. order filling, procurement or balancing against orders
• 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 30/0207 Discounts or incentives, e.g. coupons or rebates
• CPC Class Codes: G06Q 30/0224 based on user history
• CPC Class Codes: G06Q 30/0226 Incentive systems for frequent usage, e.g. frequent flyer miles programs or point systems
• CPC Class Codes: G06Q 30/0242 Determining effectiveness of advertisements
• CPC Class Codes: G06Q 30/0245 Surveys
• CPC Class Codes: G06Q 30/0251 Targeted advertisements
• CPC Class Codes: G06Q 30/0255 based on user history
• CPC Class Codes: G06Q 30/0269 based on user profile or attribute
• CPC Class Codes: G06Q 30/0273 Determination of fees for advertising
• CPC Class Codes: G06Q 30/0631 Item recommendations
• CPC Class Codes: G06Q 30/0633 Lists, e.g. purchase orders, compilation or processing
• CPC Class Codes: G06Q 50/12 Hotels or restaurants

Abstract

A method and system for using individualized customer models when operating a retail establishment is provided. The individualized customer models may be generated using statistical analysis of transaction data for the customer, thereby generating sub-models and attributes tailored to customer. The individualized customer models may be used in any aspect of a retail establishment'"'"'s operations, ranging from supply chain management issues, inventory control, promotion planning (such as selecting parameters for a promotion or simulating results of a promotion), to customer interaction (such as providing a shopping list or providing individualized promotions).

Claims

1. A computer-implemented method comprising:

accessing a customer model that stores transaction data associated with a customer;

receiving a request to generate a proposed shopping list of product categories that the customer will likely acquire on a shopping trip;

in response to the request, associating, for each of a plurality of product categories by one or more computers, at least a portion of the transaction data associated with the customer with a plurality of classifiers associated with the product category;

determining, by the one or more computers, a prediction for each classifier based at least on the transactional data, each prediction representing a probability that the customer will acquire a product from the product category on the shopping trip;

evaluating, for each of the plurality of product categories by the one or more computers, the predictions associated with the product category;

selecting a particular prediction for each product category based on the evaluation;

generating the proposed shopping list of product categories that the customer will likely acquire on the shopping trip based on the selected predictions; and

transmitting the proposed shopping list to a user device associated with the customer.

2. The computer-implemented method of claim 1, wherein the selecting a particular prediction for each product category comprises selecting the prediction for each product category that represents highest probability that the customer will acquire a product from the product category on the shopping trip.

3. The computer-implemented method of claim 1, further comprising:

generating the customer model, wherein the customer model comprises a shopping list sub-model derived from the transaction data, wherein the proposed shopping list is generated based on the shopping list sub-model.

4. The computer-implemented method of claim 1, wherein the plurality of classifiers associated with a first product category of the plurality of product categories comprises a rule-based classifier that applies one or more rules to the transaction data in order to output a prediction and a machine learning classifier that applies machine learning to the transaction data in order to output a prediction.

5. The computer-implemented method of claim 4, wherein the rule-based classifier outputs a probability that the customer will acquire a product from an associated category based on comparing a replenishment period associated with the product category to a number of days since the customer has bought a product in that category.

6. The computer-implemented method of claim 1, further comprising:

generating a promotional offer based on the customer'"'"'s transaction data and the proposed shopping list; and

transmitting the promotional offer with the proposed shopping list to the user device associated with the customer.

7. The computer-implemented method of claim 6, wherein the promotional offer is generated based on at least one of:

detecting hoarding behavior based on the customer'"'"'s transaction data,

detecting price-dependent behavior based on the customer'"'"'s transaction data,

detecting a frequency that the customer purchases one or more products on sale based on the customer'"'"'s transaction data,

detecting coupon-dependent behavior based on the customer'"'"'s transaction data, and

determining a fraction of products bought on sale based on the customer'"'"'s transaction data.

8. The computer-implemented method of claim 6,

wherein the promotional offer is generated based on at least one promotion attribute derived from the transaction data, the at least one promotion attribute selected from the group consisting of behavior analysis, brand loyalty, wallet share, price sensitivity, promotion sensitivity, product category substitution, and basket variability.

9. The computer-implemented method of claim 1, further comprising:

identifying a current context for the shopping trip; and

wherein the generating the proposed shopping list of product categories is further based on the current context.

10. The computer-implemented method of claim 9, wherein the current context is selected from the group consisting of day, date, and time.

11. The computer-implemented method of claim 1, further comprising:

receiving customer identification information from the customer;

identifying the customer based on the received customer identification information; and

associating the transaction data with the identified customer;

wherein the proposed shopping list of product categories is generated in response to identifying the customer.

12. The computer-implemented method of claim 11, further comprising:

identifying a location of the customer in an aisle of a retail establishment; and

displaying to the customer one or more product categories on the proposed shopping list based on the location of the customer.

13. A non-transitory computer-readable medium storing software comprising instructions executable by one or more computers which, upon such execution, cause the one or more computers to perform operations comprising:

accessing a customer model that stores transaction data associated with a customer;

receiving a request to generate a proposed shopping list of product categories that the customer will likely acquire on a shopping trip;

in response to the request, associating, for each of a plurality of product categories, at least a portion of the transaction data associated with the customer with a plurality of classifiers associated with the product, category;

determining a prediction for each classifier based at least on the transactional data, each prediction representing a probability that the customer will acquire a product from the product category on the shopping trip;

evaluating, for each of the plurality of product categories, the predictions associated with the product category;

selecting a particular prediction for each product category based on the evaluation;

generating the proposed shopping list of product categories that the customer will likely acquire on the shopping trip based on the selected predictions; and

transmitting the proposed shopping list to a user device associated with the customer.

14. The non-transitory computer-readable medium of claim 13, wherein the selecting a particular prediction for each product category comprises selecting the prediction for each product category that represents highest probability that the customer will acquire a product from the product category on the shopping trip.

15. The non-transitory computer-readable medium of claim 13, wherein the plurality of classifiers associated with a first product category of the plurality of product categories comprises a rule-based classifier that applies one or more rules to the transaction data in order to output a prediction and a machine learning classifier that applies machine learning to the transaction data in order to output a prediction.

16. The non-transitory computer-readable medium of claim 15, wherein the rule-based classifier outputs a probability that the customer will acquire a product from an associated category based on comparing a replenishment period associated with the product category to a number of days since the customer has bought a product in that category.

17. The non-transitory computer-readable medium of claim 13, further comprising:

generating a promotional offer based on the customer'"'"'s transaction data and the proposed shopping list; and

transmitting the promotional offer with the proposed shopping list to the user device associated with the customer.

18. The non-transitory computer-readable medium of claim 17,

wherein the promotional offer is generated based on at least one promotion attribute derived from the transaction data, the at least one promotion attribute selected from the group consisting of behavior analysis, brand loyalty, wallet share, price sensitivity, promotion sensitivity, product category substitution, and basket variability.

19. The non-transitory computer-readable medium of claim 13, further comprising:

identifying a current context for the shopping trip; and

wherein the generating the proposed shopping list of product categories is further based on the current context.

20. A system comprising:

one or more computers and one or more storage devices storing instructions that are operable, when executed by the one or more computers, to cause the one or more computers to perform operations comprising;

accessing a customer model that stores transaction data associated with a customer;

receiving a request to generate a proposed shopping list of product categories that the customer will likely acquire on a shopping trip;

in response to the request, associating, for each of a plurality of product categories, at least a portion of the transaction data associated with the customer with a plurality of classifiers associated with the product category;

determining a prediction for each classifier based at least on the transactional data, each prediction representing a probability that the customer will acquire a product from the product category on the shopping trip;

evaluating, for each of the plurality of product categories, the predictions associated with the product category;

selecting a particular prediction for each product category based on the evaluation;

generating the proposed shopping list of product categories that the customer will likely acquire on the shopping trip based on the selected predictions; and

transmitting the proposed shopping list to a user device associated with the customer.