Econometric optimization engine

• US 7,672,866 B2
• Filed: 10/17/2007
• Issued: 03/02/2010
• Est. Priority Date: 12/22/2000
• Status: Expired due to Term

• Current Assignee: Acoustic, L.P.
• Original Assignee: DemandTec Inc. (International Business Machines Corporation)
• Inventors: Venkatraman, Krishna, Lee, Hau, Delurgio, Phil, Neal, Michael, Valentine, Suzanne
• Primary Examiner(s): Patel; Jagdish N
• Application Number:
  US11/874,141
• Publication Number:
  US 20080086429A1
• Time in Patent Office: 867 Days
• Field of Search: 705/10, 705/1, 705/20
• US Class Current: 705/7.35
• CPC Class Codes: G06Q 20/201 Price look-up processing, e.g. updating
• CPC Class Codes: G06Q 30/02 Marketing; Price estimation or determination; Fundraising
• CPC Class Codes: G06Q 30/0206 Price or cost determination based on market factors
• CPC Class Codes: G06Q 30/0283 Price estimation or determination
• CPC Class Codes: G06Q 40/00 Finance; Insurance; Tax strategies; Processing of corporate or income taxes

Abstract

A preferred set of prices for a plurality of products, generally demand coefficients is provided. Cost data including activity-based costs is also received. A preferred set of prices that will provide a local optimum for the preferred set of prices which maximizes profit is then determined. In one embodiment, a sales model and a cost model are created. A plurality of rules is specified. The preferred set of prices is then determined based on the sales model, the cost model, and the plurality of rules.

Claims

1. A computer implemented method for determining a preferred set of prices for a plurality of products, useful in association with a computer system, the method comprising:

creating a sales model using a computer processor enabled to access computer readable memory from received store data, wherein the sales model includes a group sales equation and a market share equation, and storing the sales model within the computer readable memory;

creating a cost model using the computer processor from the received store data, and storing the cost model within the computer readable memory;

specifying a plurality of rules using the computer processor, and storing the plurality of rules within the computer readable memory;

calculating group sales using the group sales equation using the computer processor, and storing the calculated group sales within the computer readable memory;

calculating product margin using the market share equation using the computer processor, and storing the calculated product margin within the computer readable memory;

predict product sales, using the computer processor, by combining the calculated group sales with the calculated product margin, and storing the predicted product sales within the computer readable memory;

calculating the preferred set of prices by performing an optimization for a pricing goal, using the computer processor enabled to access the computer readable memory, wherein the optimization is based on the predicted product sales, the sales model, the cost model, and the plurality of rules, and wherein the optimization utilizes a heuristic approach to generate a feasible solution; and

setting the prices, using the computer processor, of the plurality of products to the calculated preferred set of prices.

2. The method, as recited in claim 1, wherein the store data includes at least one of point of sale information, product information or store information.

3. The method, as recited in claim 1, wherein the pricing goal includes at least one of profit goals, margin goals, or volume goals.

4. The method, as recited in claim 1, wherein the preferred set of prices is provided to the stores for setting the plurality of product'"'"'s prices.

5. The method, as recited in claim 1, wherein the cost model includes both fixed costs and variable costs.

6. The method, as recited in claim 1, wherein the heuristic approach includes repeatedly solving a problem related to the optimization, wherein the problem includes linear constraints, a set of linear constraints that approximate group price advance and decline constraints, and an objective that involves marginal contribution to profit of each product.

7. The method, as recited in claim 6, wherein the linear constraints include brand pricing, size pricing, unit pricing and line pricing.

8. The method, as recited in claim 1, further comprising grouping at least two products of the plurality of products into demand groups, wherein demand groups are groupings of products that are highly substitutable.

9. The method, as recited in claim 8, wherein the sales model is generated for the demand groups.

10. An optimization engine, useful in association with an econometric engine for creating a sales model and a financial model engine for creating a cost model, the optimization engine comprising:

computer readable memory configured to store computer code for a sales model and a cost model, wherein a econometric engine generates the sales model and a financial model engine generates the cost model;

a rule editor configured to enable the generation of rules which are stored within the computer readable memory, wherein the rules include a plurality of rule parameters;

a rule tool, which stores the plurality of rule parameters within the computer readable memory;

a price calculator connected to the rule tool, the financial model engine, the econometric engine and the computer readable memory, wherein the price calculator receives the sales model from the econometric engine via the computer readable memory and the cost model from the financial engine via the computer readable memory, wherein the sales model includes a group sales equation and a market share equation, and wherein the price calculator calculates group sales using the group sales equation and calculates product margin using the market share equation, and wherein the price calculator predicts product sales by combining the calculated group sales with the calculated product margin, and wherein the price calculator calculates a preferred set of prices by performing an optimization for a pricing goal, wherein the optimization is based on rule parameters, the sales model, the predicted product sales and the cost model, and further wherein the optimization utilizes a heuristic approach to generate a feasible solution; and

a support tool configured to set the prices of the plurality of products to the calculated preferred set of prices.

11. The optimization engine, as recited in claim 10, wherein the econometric engine and the financial model engine receive store data which includes at least one of point of sale information, product information or store information.

12. The optimization engine, as recited in claim 10, wherein the pricing goal includes at least one of profit goals, margin goals, or volume goals.

13. The optimization engine, as recited in claim 10, wherein the support tool provides the preferred pricing to the stores for setting the plurality of product'"'"'s prices.

14. The optimization engine, as recited in claim 10, wherein the cost model includes both fixed costs and variable costs.

15. The optimization engine, as recited in claim 10, wherein the heuristic approach includes repeatedly solving a problem related to the optimization, wherein the problem includes linear constraints, a set of linear constraints that approximate group price advance and decline constraints, and an objective that involves marginal contribution to profit of each product.

16. The optimization engine, as recited in claim 15, wherein the linear constraints include brand pricing, size pricing, unit pricing and line pricing.

17. The optimization engine, as recited in claim 10, wherein the econometric engine further groups at least two products of the plurality of products into demand groups, wherein demand groups are groupings of products that are highly substitutable.

18. The optimization engine, as recited in claim 17, wherein the sales model is generated for the demand groups.