# US 8,280,773 B2 · Method and apparatus for internet customer retention

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 8,280,773 B2
- Document ID: US8280773B2
- Status: Granted
- Kind: B2
- Application number: 09/804,728
- Filed: 2001-03-13
- Published: 2002-04-18
- Granted: 2012-10-02
- Earliest claimed: 2000-03-13
- Assignees: Intellions, Inc.
- Inventors: Kannan Srinivasan; Michael I. Shamos
- Web page: https://patentgrep.com/patent/US8280773B2

## CPC

- G06Q 30/02: Marketing; Price estimation or determination; Fundraising
- G06Q 30/0204: Market segmentation
- G06Q 30/0211: Determining the effectiveness of discounts or incentives
- G06Q 30/0222: {During e-commerce, i.e. online transactions}
- G06Q 30/0253: {During e-commerce, i.e. online transactions}
- G06Q 30/0254: {based on statistics}
- G06Q 30/0269: {based on user profile or attribute}
- G06Q: INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR

## Abstract

A method of dynamically optimizing customer retention for a web marketing site is provided. That method includes specifying a permissible defunct threshold, specifying a range of offers to be included in a set of promotions, determining a probability that a customer will become defunct in a predetermined period of time since the last interaction of that customer with the web site, and providing a promotion to a customer if the probability that the customer will become defunct in the predetermined period of time since the last interaction of that customer with the web site is greater than a predetermined threshold.

## Claims

### Claim 1

A computer implemented method of dynamically optimizing customer retention for a web marketing site, comprising:
operating a computer processor and memory for:
specifying a permissible defunct threshold representing a probability that a particular customer is not expected to return to the web marketing site, wherein the permissible defunct threshold is set according to an inter-login time of a customer at the web marketing site; and
responsive to the particular customer not interacting with the web marketing site for a period of time, determining a probability that the particular customer will become defunct based on historical data stored in a database indicating a percentage of customers that have returned to the web marketing site after having no interaction with the web marketing site for the period of time; and
determining that the particular customer has exceeded the defunct threshold;
sampling defunct customers to determine a promotion to offer the particular customer; and
propagating the promotion to the particular customer.

### Claim 2 (depends on 1)

The method according to claim 1, wherein the promotion is automatically propagated to the web marketing site.

### Claim 3 (depends on 1)

The method according to claim 1, wherein the promotion comprises a discount on a product that maximizes customer retention.

### Claim 4 (depends on 1)

The method according to claim 1, wherein the promotion comprises a discount on a product that maximizes profit.

### Claim 5 (depends on 1)

The method according to claim 1, wherein the sampling further comprises:
segmenting the defunct customers into socioeconomic groups; and
only sampling customers belonging to certain socioeconomic groups.

### Claim 6 (depends on 1)

The method according to claim 1, wherein the promotion comprises a discount on a product that maximizes customer retention.

### Claim 7 (depends on 6)

The method according to claim 6, wherein:
a permissible defunct threshold for customers that have previously spent more than $1000 is set lower than a permissible defunct threshold for customers that previously spent more than $50; and
the promotion is propagated to the web marketing site for offering to subsequent customers each time the promotion changes by a particular amount, as discovered via sampling, the particular amount comprising $0.25.

### Claim 8

A computer implemented method of dynamically optimizing customer retention for a web marketing site, comprising:
operating a computer processor and memory for:
specifying a permissible defunct threshold representing a probability that a particular customer is not expected to return to the web marketing site, wherein the permissible defunct threshold is set lower for customers predetermined to be important customers; and
responsive to the particular customer not interacting with the web marketing site for a period of time, determining a probability that the particular customer will become defunct based on historical data stored in a database indicating a percentage of customers that have returned to the web marketing site after having no interaction with the web marketing site for the period of time; and
determining that the particular customer has exceeded the defunct threshold;
sampling defunct customers to determine a promotion to offer the particular customer; and
propagating the promotion to the particular customer.

### Claim 9 (depends on 8)

The method according to claim 8, wherein the promotion is automatically propagated to the web marketing site.

### Claim 10 (depends on 8)

The method according to claim 8, wherein the promotion comprises a discount on a product that maximizes customer retention.

### Claim 11 (depends on 8)

The method according to claim 8, wherein the promotion comprises a discount on a product that maximizes profit.

### Claim 12 (depends on 8)

The method according to claim 8, wherein the sampling further comprises:
segmenting the defunct customers into socioeconomic groups; and
only sampling customers belonging to certain socioeconomic groups.

### Claim 13 (depends on 10)

The method according to claim 10, wherein:
a permissible defunct threshold for customers that have previously spent more than $1000 is set lower than a permissible defunct threshold for customers that previously spent more than $50; and
the promotion is propagated to the web marketing site for offering to subsequent customers each time the promotion changes by a particular amount, as discovered via sampling, the particular amount comprising $0.25.

### Claim 14

A computer implemented method of dynamically optimizing customer retention for a web marketing site, comprising:
operating a computer processor and memory for:
specifying a permissible defunct threshold representing a probability that a particular customer is not expected to return to the web marketing site; and
responsive to the particular customer not interacting with the web marketing site for a period of time, determining a probability that the particular customer will become defunct based on historical data stored in a database indicating a percentage of customers that have returned to the web marketing site after having no interaction with the web marketing site for the period of time; and
determining that the particular customer has exceeded the defunct threshold;
sampling defunct customers to determine a promotion to offer the particular customer, wherein the sampling further comprises: segmenting the defunct customers into socioeconomic groups; and only sampling customers belonging to certain socioeconomic groups; and
propagating the promotion to the particular customer.

### Claim 15 (depends on 14)

The method according to claim 14, wherein the promotion is automatically propagated to the web marketing site.

### Claim 16 (depends on 14)

The method according to claim 14, wherein the permissible defunct threshold is set according to an inter-login time of a customer at the web marketing site.

### Claim 17 (depends on 14)

The method according to claim 14, wherein the promotion comprises a discount on a product that maximizes customer retention.

### Claim 18 (depends on 14)

The method according to claim 14, wherein the promotion comprises a discount on a product that maximizes profit.

### Claim 19 (depends on 14)

The method according to claim 14, wherein the permissible defunct threshold is set lower for customers predetermined to be important customers.

### Claim 20 (depends on 14)

The method according to claim 14, wherein the promotion comprises a discount on a product that maximizes customer retention.

### Claim 21 (depends on 20)

The method according to claim 20, wherein:
a permissible defunct threshold for customers that have previously spent more than $1000 is set lower than a permissible defunct threshold for customers that previously spent more than $50; and
the promotion is propagated to the web marketing site for offering to subsequent customers each time the promotion changes by a particular amount, as discovered via sampling, the particular amount comprising $0.25.
