Automatically generating an optimal marketing strategy for improving cross sales and upsales of items

Patent metadata

Field	Value
Publication number	US-9685048-B2
Application number	US-86227907-A
Country	US
Kind code	B2
Filing date	Sep 27, 2007
Priority date	Apr 3, 2007
Publication date	Jun 20, 2017
Grant date	Jun 20, 2017

Abstract

A computer implemented method, apparatus, and computer usable program product for generating an optimized marketing strategy for improving sales. The process parses event data to identify patterns of events associated with a selection of a selected item by each customer in a plurality of customers and selection of at least one item in a set of items related to the selected item. The process identifies events in the patterns of events that result in a purchase of at least one item in the set of related items by the customers to form optimized events. The process then generates a marketing strategy using the optimized events. The marketing strategy comprises a set of strategies for increasing purchases of items in the set of related items by the customers.

First claim

What is claimed is:

1. A computer implemented method for generating an optimized marketing strategy for improving sales, the computer implemented method comprising:
identifying an item in a plurality of items selected for purchase by each customer in a plurality of customers associated with a retail facility to form a selected item;
identifying at least one item in the plurality of items selected for purchase by each customer in the plurality of customers that is related to the selected item to form a set of related items;
parsing event data associated with the plurality of customers to identify patterns of events associated with a selection of the selected item by each customer in the plurality of customers, wherein the event data comprises metadata describing events associated with the plurality of customers and the plurality of items;
parsing the event data associated with the plurality of customers to identify patterns of events associated with a selection of at least one item in the set of related items by customers in the plurality of customers;
identifying, by a processing unit, events in the patterns of events associated with the selection of the selected item and in the patterns of events associated with the selection of the at least one item in the set of related items, wherein the events result in a purchase of at least one item in the set of related items by the customers to form optimized events, and wherein the purchase of the at least one item in the set of related items by the customers results in an increase in profit or an increase in revenue; and
generating a marketing strategy using the optimized events, wherein the marketing strategy comprises a set of strategies for increasing purchases of items in the set of related items by the customers.

2. The computer implemented method of claim 1 wherein at least one item in the set of related items is an upsale item, wherein the upsale item provides a same basic functionality as the selected item, wherein a sale of the upsale item to the customers produces a greater amount of revenue or a greater amount of profit than a sale of the selected item, and further comprising:
prompting the customers, by the marketing strategy, to purchase the upsale item instead of the selected item.

3. The computer implemented method of claim 2 wherein the upsale item comprises at least one of a different size than a size of the selected item, a different brand than a brand of the selected item, a different number of constituent parts than a number of constituent parts of the selected item, a different price than a price of the selected item, a different packaging than a packaging of the selected item, and an additional feature that is not provided by the selected item.

4. The computer implemented method of claim 1 wherein at least one item in the set of related items is a correlated item, wherein the correlated item provides a different basic functionality than the selected item, and further comprising:
prompting the customers, by the marketing strategy, to purchase the correlated item in addition to a purchase of the selected item.

5. The computer implemented method of claim 1 further comprising:
identifying the plurality of items and the plurality of customers;
analyzing the plurality of items using a set of correlation analysis techniques to identify different items that are purchased in correlation with one or more other items in the plurality of items to form the set of related items.

6. The computer implemented method of claim 1 further comprising:
identifying customers in the plurality of customers;
analyzing customer profiles for the plurality of customers to identify types of customers in the plurality of customers;
associating types of customers with a purchase of each item in the set of related items; and
identifying the events in the patterns of events that result in the purchase of the at least one item in the set of related items by the types of customers to form optimized events, wherein the optimized events are events associated with increasing sales of items in the set of related items by a particular type of customer.

7. The computer implemented method of claim 6 wherein the type of customers comprises at least one of an age range, an occupation type, an income bracket, a family size, an education level, a number of children, a marital status, an average amount of money spent during each transaction at the retail facility, and a demographic group.

8. The computer implemented method of claim 1 further comprising:
receiving biometric data for a set of customers in the plurality of customers from a set of biometric detection devices associated with the retail facility; and
analyzing the biometric data with the event data to generate the marketing strategy.

9. The computer implemented method of claim 8 further comprising:
detecting a change in biometric readings associated with the set of customers that exceeds a threshold change; and
responsive to a determination that the customers were viewing the selected item, an item in the set of related items, a display, or a marketing message when the change in the biometric readings occurred, associating the change in the biometric readings with the selected item, the item in the set of related items, or the marketing message to form the biometric data.

10. The computer implemented method of claim 1 wherein the optimized marketing strategy specifies a placement of a display device, and further comprising:
displaying a marketing message for the at least one item in the set of related items on the display device, wherein the marketing message includes a location of the at least one item in the retail facility.

11. The computer implemented method of claim 1 further comprising:
identifying, by the optimized marketing strategy, a set of locations in the retail facility for placement of items in the set of related items, wherein the set of locations are optimized locations to increase a probability that a customer will purchase the at least one item in the set of related items.

12. The computer implemented method of claim 1 further comprising:
receiving video data in a continuous stream from a set of cameras associated with the retail facility; and
analyzing the video data, by a smart analysis engine, to form the event data, wherein analyzing the video data comprises generating the metadata describing the events.

13. The computer implemented method of claim 12 wherein analyzing the video data further comprises:
receiving detection data from a set of detectors located outside the retail facility;
analyzing the detection data to form external data; and
processing the external data with the video data to form the event data.

14. A computer program product comprising:
a computer usable storage device having computer usable program code embodied therewith for generating an optimized marketing strategy for improving sales, the computer usable program code comprising:
computer usable program code for identifying an item in a plurality of items selected for purchase by each customer in a plurality of customers associated with a retail facility to form a selected item;
computer usable program code for identifying at least one item in the plurality of items selected for purchase by each customer in the plurality of customers that is related to the selected item to form a set of related items;
computer usable program code for parsing event data associated with the plurality of customers to identify patterns of events associated with a selection of the selected item by each customer in the plurality of custome

Assignees

• Angell Robert Lee
• Kraemer James R
• IBM

Inventors

• Angell Robert Lee
• Kraemer James R

Classifications

• G06Q30/0201

  Market modelling; Market analysis; Collecting market data · CPC title

• G06Q10/06375

  Prediction of business process outcome or impact based on a proposed change · CPC title

• G06Q30/0204

  Market segmentation · CPC title

• G07G1/00 Primary

  Cash registers · CPC title

• G06Q30/02

  Marketing; Price estimation or determination; Fundraising · CPC title