Method and apparatus for optimizing promotional sale of products based upon historical data
AssigneeNCR Corporation
InventorsScott W. Cunningham, Randy G. Kerber
Life of this patent
Estimating the term…
Abstract
A system for optimizing the promotional sale of a product, a product segment, or a category which may take into account related products or competing products comprising means for generating a three-dimensional data structure corresponding to the sales history for a product, the data structure dimensions corresponding to an event type domain, a time domain, and a unit of measurement domain, means for populating the three-dimensional data structure, a neural network, means for training the neural network and means for applying sales objectives and constraints to the neural network.
Claims12
A system for optimizing the promotional sale of a product, wherein each product has an associated sales history, comprising:
- (a) means for generating a three-dimensional data structure corresponding to the sales history for a product, the data structure dimensions corresponding to an event type domain, a time domain, and a unit of measurement domain;
- (b) means for populating the three-dimensional data structure, wherein each element of the three-dimensional data structure is the sales history of the product for the corresponding event type, time and unit measurement;
- (c) a neural network;
- (d) means for training the neural network with the three-dimensional data structure;
- and
- (e) means for applying sales objectives and constraints to the neural network. thereby generating a promotional plan for the product.
A system for optimizing the promotional sale of a product segment, wherein each product segment is a group of products to be promoted together, each product having an associated sales history, the system comprising:
- (a) means for generating a three-dimensional data structure corresponding to the sales history for a product segment, the data structure dimensions corresponding to an event type domain, a time domain, and a unit of measurement domain;
- (b) means for populating the three-dimensional data structure, wherein each element of the three-dimensional data structure is an aggregate of the sales history of the products within the product segment for the corresponding event type, time and unit measurement;
- (c) a neural network;
- (d) means for training the neural network with the three-dimensional data structure;
- and
- (e) means for applying sales objectives and constraints to the neural network, thereby generating a promotional plan for the product segment.
A system for optimizing the promotional sale of a manufacturer's product segment taking into account sales of competing manufacturer's products in the same product segment, wherein each product segment is a group of products to be promoted together, and each product has an associated sales history and manufacturer, the system comprising:
- (a) means for generating a plurality of three-dimensional data structures, each three-dimensional data structure corresponding to the sales history for a product segment for a particular manufacturer, each data structure dimensions corresponding to an event type domain, a time domain, and a unit of measurement domain;
- (b) means for populating the three-dimensional data structure, wherein each element of each three-dimensional data structure is an aggregate of the sales history of the products within the product segment for the corresponding event type, time and unit measurement for the corresponding manufacturer;
- (c) a neural network;
- (d) means for training the neural network with the plurality of the three-dimensional data structures;
- and
- (e) means for applying sales objectives and constraints to the neural network for a selected manufacturer, thereby generating a promotional plan for the segment taking into consideration the sales of products by competing manufacturers.
A system for optimizing the promotional sale of a product segment for a particular manufacturer taking into account sales of competing manufacturer's products in the same segment and of related products by the particular manufacturer, wherein each segment is a group of products to be promoted together, and each product has an associated sales history and manufacturer, the system comprising:
- (a) means for generating a two-dimensional data structure, the data structure dimensions corresponding to manufacturer domain and a segment domain of a product;
- (b) means for populating the three-dimensional data structure linked to the two-dimensional data structure, the three-dimensional data structure corresponding to the sales history for a product segment for a manufacturer, the data structure dimensions corresponding to an event type domain, a time domain, and a unit of measurement domain;
- (c) means for populating the three-dimensional data structure, wherein each element of the three-dimensional data structure is an aggregate of the sales history of the products within the product segment for a manufacturer for the corresponding event type, time and unit of measurement;
- (d) a neural network;
- (e) means for training the neural network with the three-dimensional data structure;
- and
- (f) means for applying sales objectives and constraints to the neural network, thereby generating a promotional plan for the segment taking into consideration the sales of products in the same segment by competing manufacturers and the sale of related products by the particular manufacturer.
A process for automatically optimizing the promotional sale of a product utilizing a computer system, wherein each product has an associated sales history, comprising the steps of:
- (a) generating a three-dimensional data structure corresponding to the sales history for a product, the data structure dimensions corresponding to an event type domain, a time domain, and a unit of measurement domain;
- (b) populating the three-dimensional data structure, wherein each element of the three-dimensional data structure is an aggregate of the sales history of the products within the product segment for the corresponding event tape, time and unit measurement;
- (c) training a neural network with the three-dimensional data structure;
- and
- (d) applying sales objectives and constraints to the neural network, thereby generating a promotional plan for the product segment.
A process for automatically optimizing the promotional sale of a product segment utilizing a computer system, wherein each product segment is a group of products to be promoted together, each product having an associated sales history, the process comprising the steps of:
- (a) generating a three-dimensional data structure corresponding to the sales history for a product segment, the data structure dimensions corresponding to an event type domain, a time domain, and a unit of measurement domain;
- (b) populating the three-dimensional data structure, wherein each element of the three-dimensional data structure is an aggregate of the sales history of the products within the product segment for the corresponding event type, time and unit measurement;
- (c) training the neural network with the three-dimensional data structure;
- and
- (d) applying sales objectives and constraints to the neural network, thereby generating a promotional plan for the product segment.
A process for automatically optimizing the promotional sale of a manufacturer's product segment taking into account sales of competing manufacturer's products in the same product segment, wherein each product segment is a group of products to be promoted together, and each product has an associated sales history and manufacturer, the process comprising the steps of:
- (a) generating a plurality of three-dimensional data structures, each three-dimensional data structure corresponding to the sales history for a product segment for a particular manufacturer, each data structure dimensions corresponding to an event type domain, a time domain, and a unit of measurement domain;
- (b) populating the three-dimensional data structure, wherein each element of each three-dimensional data structure is an aggregate of the sales history of the products within the product segment for the corresponding event type, time and unit measurement for the corresponding manufacturer;
- (c) training the neural network with the plurality of the three-dimensional data structures;
- and
- (d) applying sales objectives and constraints to the neural network for a selected manufacturer, thereby generating a promotional plan for the segment taking into consideration the sales of products by competing manufacturers.
A process for automatically optimizing the promotional sale of a product segment for a particular manufacturer taking into account sales of competing manufacturer's products in the same segment and of related products by the particular manufacturer, wherein each segment is a group of products to be promoted together, and each product has an associated sales history and manufacturer, the process comprising the steps of:
- (a) generating a two-dimensional data structure, the data structure dimensions corresponding to a manufacturer domain and a segment of a product;
- (b) generating a three-dimensional data structure linked to the two-dimensional data structure, the three-dimensional data structure corresponding to the sales history for a product segment for a manufacturer, the data structure dimensions corresponding to an event type domain, a time domain, and a unit of measurement domain;
- (c) populating the three-dimensional data structure, wherein each element of the three-dimensional data structure is an aggregate of the sales history of the products within the product segment for a manufacturer for the corresponding event type, time and unit of measurement;
- (d) training the neural network with the three-dimensional data structure;
- and
- (e) applying sales objectives and constraints to the neural network, thereby generating a promotional plan for the segment taking into consideration the sales of products in the same segment by competing manufacturers and the sale of related products by the particular manufacturer.
Dependencies are inferred from the claim text.