System and Method for Generating Demand Groups

• US 20100228604A1
• Filed: 03/09/2010
• Published: 09/09/2010
• Est. Priority Date: 12/20/2000
• Status: Active Grant

• Current Assignee: Acoustic, L.P.
• Original Assignee: International Business Machines Corporation
• Inventors: Desai, Paritosh, Gajendran, Kamal
• Granted Patent: US 9,785,953 B2
• Time in Patent Office: Days
• US Class Current: 705/10
• 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 30/0205 Location or geographical consideration

Abstract

The present invention relates to a system and method for generating demand groups. The demand groups may then be fed to downstream pricing optimization and/or business decision systems. The system receives demand group modeling data including a product listing, point of sales data, available econometric data and product information. Attributes may then be assigned to the products based upon product identifiers, size, flavor, brand, and product descriptions utilizing natural language processing. The products may then be clustered according to the attributes and point of sales data utilizing any of hierarchical clustering, k-means clustering, locality sensitive hashing, QT clustering, EM algorithms and model based clustering. One or more decision trees may be generated for the product listings using the point of sales data. Demand rules may be received, which may be applied to the product clusters and the decision trees to generate demand groups. A confidence score may be generated for each product indicating how well that product fits within the demand group. These confidence scores may be compared against a threshold. Products with scores below the threshold may be flagged for user review.

Claims

1. A computer implemented method for generation of demand groups, useful in association with a price optimization system, the method comprising:

receiving a product listing;

receiving product data for products in the product listing;

receiving point of sales data;

assigning attributes to the products based upon the product data;

clustering the products by received point of sales data and the assigned attributes;

generating a decision tree for the product listing utilizing the point of sales data;

receiving at least one demand rule; and

generating the demand groups by applying the received at least one demand rule to at least one of the decision tree and the product clusters.

2. The method for generating the demand groups, as recited in claim 1, further comprising receiving a confidence threshold for the generation of the demand groups.

3. The method for generating the demand groups, as recited in claim 2, further comprising generating a confidence level for each product, wherein the confidence level indicated how accurate the placement of the product in the demand group is.

4. The method for generating the demand groups, as recited in claim 3, further comprising comparing the confidence level of each product to the confidence threshold, and when the confidence level is below the confidence threshold flagging the product for user review.

5. The method for generating the demand groups, as recited in claim 1, wherein the clustering the products utilizes at least one of hierarchical clustering, k-means clustering, locality sensitive hashing, QT clustering, EM algorithms and model based clustering.

6. The method for generating the demand groups, as recited in claim 5, further comprising assigning weights to the assigned attributes, wherein the weights are used by the clustering of the products.

7. The method for generating the demand groups, as recited in claim 6, further comprising updating the assigned attributes when new product data becomes available.

8. The method for generating the demand groups, as recited in claim 7, wherein the updated attributes weights are set between the old weights and the weights of the new product data.

9. The method for generating the demand groups, as recited in claim 1, wherein the assigning attributes to the products includes assigning attributes by at least one of a product identifier, product size, customer hierarchy, flavor and product descriptors.

10. The method for generating the demand groups, as recited in claim 9, wherein assigning attributes by the product descriptors includes natural language processing.

11. The method for generating the demand groups, as recited in claim 1, wherein the demand rules include at least one of a prioritization of size, type and brand for the division of products into the demand groups.

12. The method for generating the demand groups, as recited in claim 1, wherein generating demand groups using decision trees includes measuring distance of products to one another in the decision tree.

13. The method for generating the demand groups, as recited in claim 1, wherein generating demand groups includes clustering products according to a transition matrix.

14. A system for generation of demand groups, useful in association with a price optimization system, the system comprising:

an econometric coefficient analyzer configured to receive a product listing and point of sales data;

an attribute engine configured to receive product data for products in the product listing, and further configured to assign attributes to the products based upon the product data;

a clustering engine configured to cluster the products by received point of sales data and the assigned attributes;

a decision tree generator configured to generate a decision tree for the product listing utilizing the point of sales data;

a rule interface configured to receive at least one demand rule; and

a rule based engine configured to generate the demand groups by applying the received at least one demand rule to at least one of the decision tree and the product clusters.

15. The system for generating the demand groups, as recited in claim 14, wherein the rule based engine is further configured to receive a confidence threshold for the generation of the demand groups.

16. The system for generating the demand groups, as recited in claim 15, wherein the rule based engine is further configured to generate a confidence level for each product, wherein the confidence level indicated how accurate the placement of the product in the demand group is.

17. The system for generating the demand groups, as recited in claim 16, wherein the rule based engine is further configured to compare the confidence level of each product to the confidence threshold, and when the confidence level is below the confidence threshold flagging the product for user review.

18. The system for generating the demand groups, as recited in claim 14, wherein the clustering engine utilizes at least one of hierarchical clustering, k-means clustering, locality sensitive hashing, QT clustering, EM algorithms and model based clustering.

19. The system for generating the demand groups, as recited in claim 18, further comprising a weighting engine configured to assign weights to the assigned attributes, wherein the weights are used by the clustering of the products.

20. The system for generating the demand groups, as recited in claim 18, wherein the weighting engine updates the assigned attributes when new product data becomes available.

22. The system for generating the demand groups, as recited in claim 14, wherein the assigning attributes to the products includes assigning attributes by at least one of a product identifier, product size, customer hierarchy, flavor and product descriptors.

23. The system for generating the demand groups, as recited in claim 22, wherein attribute engine includes a natural language processor configured to assign attributes from the product descriptors using natural language processing.

24. The system for generating the demand groups, as recited in claim 14, wherein the demand rules include at least one of a prioritization of size, type and brand for the division of products into the demand groups.

25. The system for generating the demand groups, as recited in claim 14, wherein generating demand groups using decision trees includes measuring distance of products to one another in the decision tree.

26. The system for generating the demand groups, as recited in claim 14, wherein generating demand groups includes clustering products according to a transition matrix.

21. The system for generating the demand groups, as recited in claim 21, wherein the weighting engine sets updated attributes weights between the old weights and the weights of the new product data.