Domain Driven Data Mining to Improve Promotional Campaign ROI and Select Marketing Channels

Post on 23-Feb-2016

30 views 0 download

description

Domain Driven Data Mining to Improve Promotional Campaign ROI and Select Marketing Channels . Presenter : Tsai Tzung Ruei Authors: Thomas Piton, Julien Blanchard, Henri Briand and Fabrice Guillet. 國立雲林科技大學 National Yunlin University of Science and Technology. CIKM.2009. Outline. - PowerPoint PPT Presentation

Transcript of Domain Driven Data Mining to Improve Promotional Campaign ROI and Select Marketing Channels

Intelligent Database Systems Lab

N.Y.U.S.T.

I. M.

Domain Driven Data Mining to Improve Promotional Campaign ROI and Select Marketing Channels

Presenter : Tsai Tzung Ruei Authors: Thomas Piton, Julien Blanchard, Henri Briand and Fabrice Guillet

CIKM.2009

國立雲林科技大學National Yunlin University of Science and Technology

Intelligent Database Systems Lab

N.Y.U.S.T.

I. M.Outline

Motivation Objective Methodology Experiments Conclusion Comments

2

Intelligent Database Systems Lab

N.Y.U.S.T.

I. M.Motivation

For each customer, there may be a large number of possible actions that can be applied . But actions, such as emailing, direct mailing and salespersons’ visits cost the company money .

To overcome this drawback, marketing managers need to acquire relevant knowledge on a one-to-one basis to decide which are the most effective communication channels to use for each customer.

3

Intelligent Database Systems Lab

N.Y.U.S.T.

I. M.Objective

To propose an actionable knowledge discovery methodology, for one-to-one marketing, which allows to contact the right customer through the right communication channel.

4

RigrhtRigrht

Intelligent Database Systems Lab

N.Y.U.S.T.

I. M.Methodology

THE RIGHT CUSTOMER

5

Intelligent Database Systems Lab

N.Y.U.S.T.

I. M.Methodology

Naive profit curve

6

Intelligent Database Systems Lab

N.Y.U.S.T.

I. M.Methodology

Choice of marketing channels

7

Intelligent Database Systems Lab

N.Y.U.S.T.

I. M.Methodology

Model generation

8

KIKR

Intelligent Database Systems Lab

N.Y.U.S.T.

I. M.Methodology

Model interpretation

9

Intelligent Database Systems Lab

N.Y.U.S.T.

I. M.Experiments

Model application

10

Intelligent Database Systems Lab

N.Y.U.S.T.

I. M.Experiments

Model validation

11

Intelligent Database Systems Lab

N.Y.U.S.T.

I. M.Experiments

During the previous operation, the rate of buyers was 18 %. Whereas in the last one, by applying our methodology, the rate of buyers raised up to 22 %, the turnover was increased by 5 %, and 115 new customers participated, representing about 1 200 000 euros of additional turnover.

12

Intelligent Database Systems Lab

N.Y.U.S.T.

I. M.Conclusion

MAJOR CONTRIBUTION To offer effective solutions to extract actionable knowledge to

intelligent CRM for companies.

FUTURE WORK To try to combine other methods of data mining to improve our

methodology (associations rules for instance) with customer purchasing potential, with a view of preventing customer ”churning” during promotional campaigns, and of suggesting high profit materials to customers with the highest tendency.

13

Intelligent Database Systems Lab

N.Y.U.S.T.

I. M.Comments

Advantage To improve customer relationship

Drawback …..

Application MRM, CRM

14