Data mining for managing marketing resources

• US 7,424,439 B1
• Filed: 09/22/1999
• Issued: 09/09/2008
• Est. Priority Date: 09/22/1999
• Status: Expired due to Fees

• Current Assignee: Microsoft Technology Licensing LLC (Microsoft Corporation)
• Original Assignee: Microsoft Corporation
• Inventors: Fayyad, Usama M., Ojjeh, Bassel Y.
• Primary Examiner(s): TARAE, CATHERINE MICHELLE
• Application Number:
  US09/401,439
• Time in Patent Office: 3,275 Days
• Field of Search: 705/7, 705/10, 705/14, 707/1, 707/100, 707/5
• US Class Current: 705/7.33
• CPC Class Codes: G06Q 30/02 Marketing; Price estimation or determination; Fundraising
• CPC Class Codes: G06Q 30/0204 Market segmentation

Abstract

Data mining for managing marketing resources is disclosed. In one embodiment, a method for managing a marketing campaign includes the following. First, the method provides a data mining engine capable of being trained with training data and capable thereof of performing inference relative to the training data and on future data. Next, the method provides a user database defining observed characteristics of each one of a set of users. The characteristics include at least one of one or more user'"'"'s attributes, and one or more of the user'"'"'s preferences. Finally, the data mining engine is trained with a set of training data comprising the user data base, and a predetermined characteristic pertaining to the market campaign is input to the engine, such that, in response to the input, a subset of the users in the database is obtained that have the highest correlation to the characteristic.

Claims

1. A method for managing a marketing campaign, comprising:

providing a data mining engine capable of being trained with training data; and

capable thereafter of performing inferences relative to the training data and on additional data;

providing a user database containing observed characteristics of each one of a set of users, the characteristics comprising at least one of;

(a) at least one of the user'"'"'s attributes, (b) at least one of the user'"'"'s preferences;

training the data mining engine with a set of training data comprising the user database by clustering the user database into different segments of users distinguished by different states of one or more characteristics;

inputting to the data mining engine a predetermined set of characteristics including a predetermined set of user attributes likely to pertain to a product to which the marketing campaign is directed and, in response thereto, obtaining from the data mining engine a subset of the users in the database having the highest correlation to the characteristic by determining which of the segments found during clustering of the user database has the highest statistical correlation to the predetermined set of characteristics;

determining in the data mining engine a set of prevalent attributes of the subset of users;

defining a target database of users and determining in the data mining engine a target subset of users in the target database statistically correlated to the set of prevalent attributes;

conducting a presently conducted marketing campaign cycle directed at the target subset of users;

observing and analyzing responses of the target subset of users to the presently conducted marketing campaign cycle at least partly in real-time;

forming a focused group of the target subset of users whose observed response was a particular type of response;

determining, in the data mining engine, a group of prevalent characteristics of the focused group of users; and

defining a database to be mined and determining, in the data mining engine, a new set of users in the database to be mined whose characteristics are statistically correlated with the group of prevalent characteristics,

determining, in the data mining engine, a complete set of statistically prevalent user attributes of the subset of users;

for any member of the subset of users having certain attributes which are undetermined in the user data base, filling in the certain undetermined attributes with the corresponding ones of the complete set of statistically prevalent user attributes of the subset of users.

2. The method of claim 1 wherein the target database comprises the user database with which the data mining engine has been trained.

3. The method of claim 1 wherein the target database comprises an additional database not included in the user database, the additional data base defining characteristics of a set of new users.

4. The method of claim 1 wherein the database to be mined comprises the user database with which the data mining engine was trained.

5. The method of claim 1 wherein the database to be mined comprises the target data base of users.

6. The method of claim 1 wherein the database to be mined comprises a new database not included in either the user data base nor in the target user database.

7. The method of claim 1 further comprising:

directing a subsequent marketing campaign cycle to the new set of users.

8. The method of claim 1 wherein the user preference corresponds to a prior purchase of a product which is a subject of the marketing campaign.

9. The method of claim 1 further comprising:

for any member of the target subset of users having certain attributes which are undetermined, filling in the certain undetermined attributes with the corresponding ones of the set of prevalent user attributes of the subset of users.

10. The method of claim 1 wherein clustering comprises:

providing with a visualization tool a tabulation of characteristics of each cluster with the probability of each characteristic in the cluster;

labeling each cluster with a statistically predominant characteristic thereof in accordance with the tabulation.

11. The method of claim 10 wherein the statistically predominant characteristic of each cluster distinguishes the cluster from the other clusters.

12. A machine-readable medium having instructions stored thereon for execution by a processor to perform a method comprising:

providing a data mining engine capable of being trained with training data and capable thereafter of performing inferences relative to the training data; and

on additional data;

providing a user database defining the observed characteristics of each one of a set of users, the characteristics comprising at least one of;

(a) at least one of the user'"'"'s attributes, (b) at least one of the user'"'"'s preferences;

training the data mining engine with a set of training data comprising the user database by clustering the user data base into different segments of user distinguished by different states of a characteristic;

inputting to the data mining engine a predetermined set of characteristics including a predetermined set of user attributes likely to pertain to a product to which the marketing campaign is directed and, in response thereto, obtaining from the data mining engine a subset of the users in the data base having the highest correlation to the characteristic by determining which of the segments found during clustering of the user database has the highest statistical correlation to the predetermined characteristic;

determining in the data mining engine a set of prevalent attributes of the subset of users;

defining a target database of users and determining in the data mining engine a target subset of users in the target data base statistically correlated to the set of prevalent;

conducting and analyzing a presently conducted marketing campaign cycle directed at the target subset of users at least partly in real-time;

observing responses of the target subset of users to the presently conducted marketing campaign cycle;

forming a focused group of the target subset of users whose observed response was a particular type of response;

determining, in the data mining engine, a group of prevalent characteristics of the focused group of users; and

defining a database to be mined and determining, in the data mining engine, a new set of users in the database to be mined whose characteristics are statistically correlated with the group of prevalent characteristics,

determining, in the data mining engine, a complete set of statistically prevalent user attributes of the subset of users;

for any member of the subset of users having certain attributes which are undetermined in the user data base, filling in the certain undetermined attributes with the corresponding ones of the complete set of statistically prevalent user attributes of the subset of users.