Data processing: financial – business practice – management – or co – Automated electrical financial or business practice or... – Discount or incentive
Reexamination Certificate
2000-11-07
2003-09-16
Myhre, James W. (Department: 3622)
Data processing: financial, business practice, management, or co
Automated electrical financial or business practice or...
Discount or incentive
C705S014270
Reexamination Certificate
active
06622125
ABSTRACT:
BACKGROUND OF THE INVENTION
1. Field of the Invention
This invention relates generally to sales promotion systems and, more particularly, to real-time automatic selection of sales promotions based on analysis of previous customer purchases.
2. Description of the Related Art
Sales promotions can encompass a wide variety of different actions and procedures designed to stimulate product sales. Sales promotion include, for example, in-store purchase suggestions from sales clerks, limited-time price reductions on items, in-store announcements of products over public address systems, coupons distributed in a store to shoppers or distributed via newspaper and magazine inserts to readers for future redemption with a purchase, and more sophisticated multimedia programs presented over special display kiosks that play to passers-by. Decisions on particular sales promotions to be employed are frequently made as part of a national or regional marketing campaign in which data concerning sales trends might be studied to discern patterns that could help in the sales promotion decision. Often, the sales promotion to be used at a particular store and the time at which the promotion will be used are left to management at each store or to individual sales clerks and other store personnel.
Trends in purchases are sometimes relatively simple to observe. For example, there typically is a seasonal need for particular items, such as coats during winter or sandals during summer. Both national and local marketing campaigns might choose to call attention to such items through a sales promotion comprising a temporary price reduction. Presumably, customers will be motivated by the seasonal need and by the price reduction to purchase the items, thereby creating higher volume sales and increased profits. Another example of an in-store sales promotion is one that occurs after a sales clerk completes a transaction for the purchase of an item by suggesting the purchase of a complementary item. A typical suggestion occurs when, for example, a clerk suggests the purchase of an electric light bulb after a customer has already purchased a lamp or suggests a sauce or topping to go along with a purchased food entree. Given a set of sales promotions from which a promotion is selected, a better quality selection is one that is more likely to result in an additional purchase.
The quality of a sales promotion selection can vary greatly in accordance with the skill of the individual making the selection. For example, individual sales clerks and store managers can vary greatly in their ability to recognize opportunities in particular purchase transactions by customers and can be at an extreme disadvantage in attempting to recognize trends across a larger customer population to fashion promotional campaigns. Making the selection of sales promotions more centralized can be advantageous in that persons more highly skilled in discerning buying patterns can be brought to bear on the problem and data from a wide customer population can be gathered and analyzed for such patterns. This would likely result in better identification of buyer preferences and would thereby improve the quality of the selection.
Analysis of sales data to discern buyer preferences is known, but unfortunately takes place relatively far removed in time from the retail customer. That is, the sales data must be gathered, analyzed, and used to generate selection criteria for sales promotions and any trend revealed in the data might have come to a halt by the time conventional analysis is completed. This is especially true in the case of seasonal trends, which might not be identified as seasonal until the purchasing fervor for an item has ended. Moreover, the generation of selection criteria can be problematic, as the recognition of trends in the sales data can be highly dependent on the skill of individual analysts.
It would be advantageous to permit analysis of sales data and recognition of trends to occur closer to the retail end of the distribution chain. This would permit selection of a sales promotion to be based on relatively recent customer purchases and timely identification of emerging trends. It also would be advantageous if the selection of a sales promotion could occur in real time at the point of customer purchase or store entry, further enhancing the timeliness of the sales promotion selection process. Finally, it would be advantageous to automate the selection process, thereby removing individual skill at the local level from influencing the selection and permitting greater data analysis to take place.
From the discussion above, it should be apparent that there is a need for a system that automatically selects sales promotions, both in-store and telemarketing, based on analysis of previous customer purchases on a real-time basis. The present invention satisfies this need.
SUMMARY OF THE INVENTION
In accordance with the invention, an automated sales promotion selection system uses computer-implemented artificial neural networks, hereafter referred to as neural networks, neural nets, or simply nets, to identify desirable sales promotions based on recent customer purchases. The system includes a customer information device that receives customer data relating to customer purchases of items from an inventory of items, a central processing unit having a sales promotion neural network and a storage unit containing a plurality of item identifiers comprising potential customer purchases of additional items from the inventory, and an output device that receives the item identifiers of the likely purchases determined by the sales promotion neural network and produces a sales promotion relating to at least one of the item identifiers. The sales opportunity neural network responds to customer data received from the customer information device by determining if one or more of the item identifiers in the storage unit corresponds to an item likely to be purchased by one of the customers,
In one aspect of the invention, an automated sales promotion system selects item identifiers of potential purchases for a customer by using neural networks to place the items purchased by the customer into predetermined and adaptable purchase groups comprising items that are frequently purchased together and to determine items that are not among the purchased items and that otherwise would comprise one of the predetermined purchase groups. The system then automatically selects the items determined to be missing as the item identifiers of potential customer purchases. The missing items can then be suggested by a sales clerk for purchase or can be the subject of an automatically produced promotion, such as a coupon that can be redeemed for a discounted purchase price.
In another aspect of the invention, customer data is generated by training a demographics neural network that generates an output set of data defining predicted purchases of customers during a purchasing transaction, the trained neural network is then provided with prediction data comprising the current date, current time of day, and environmental information, and another neural network is used to predict customer purchases.
Other features and advantages of the present invention should be apparent from the following description of the preferred embodiment, which illustrates, by way of example, the principles of the invention.
REFERENCES:
patent: 4630108 (1986-12-01), Gomersall
patent: 4833308 (1989-05-01), Humble
patent: 4908761 (1990-03-01), Tai
patent: 4910672 (1990-03-01), Off et al.
patent: 4930077 (1990-05-01), Fan
patent: 5057915 (1991-10-01), Von Kohorn
patent: 5124911 (1992-06-01), Sack
patent: 5299115 (1994-03-01), Fields et al.
patent: 5353218 (1994-10-01), De Lapa et al.
patent: 5353219 (1994-10-01), Mueller et al.
patent: 5383111 (1995-01-01), Homma et al.
patent: 5390281 (1995-02-01), Luciw et al.
patent: 5401946 (1995-03-01), Weinblatt
patent: 5459306 (1995-10-01), Stein et al.
patent: 5473732 (1995-12-01), Chang
patent: 5482139 (1996-01-01), Rivalto
patent: 5504675 (1996-04-01), Cragun et al.
pate
Cragun Brian John
Kelsey Todd Mark
Lund Stephen Hollis
International Business Machines - Corporation
Myhre James W.
Wood Herron & Evans LLP
LandOfFree
Automatic sales promotion selection system and method does not yet have a rating. At this time, there are no reviews or comments for this patent.
If you have personal experience with Automatic sales promotion selection system and method, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Automatic sales promotion selection system and method will most certainly appreciate the feedback.
Profile ID: LFUS-PAI-O-3065889