Using decision tree and association rules to predict cross selling opportunities

Author

Yang, Xue-cheng ; Wu, Jun ; Zhang, Xiao-hang ; Lu, Ting-jie

Author_Institution

Sch. of Econ. & Manage., Beijing Univ. of Posts & Telecommun., Beijing

Volume

3

fYear

2008

fDate

12-15 July 2008

Firstpage

1807

Lastpage

1811

Abstract

In saturated markets cross selling offers a number of benefits to companies. While these benefits are recognized by mobile telecommunications companies, many have not fully embraced the concept in practice. This paper focuses on the prediction of cross selling opportunities and presents an innovative approach to forecast cross selling opportunities more effectively. The proposed approach combines decision tree and association rule to discover cross selling opportunity of a new service, WAP. The analysis is based on a sample of 969,228 customers selected at random from the data warehouse of a local mobile telecommunications vendor in China Mainland. The results showed that this approach can greatly improve the accuracy rate of forecasting and help telecommunications vendors make cross selling policies effectively.

Keywords

data mining; decision trees; purchasing; retailing; telecommunication services; association rules; cross selling opportunity; decision tree; forecasting accuracy rate; saturated markets; telecommunications vendor; wireless application protocol; Association rules; Communication industry; Cybernetics; Data mining; Decision trees; Economic forecasting; Machine learning; Predictive models; Telecommunication services; Wireless application protocol; Association Rule; Cross Selling; Decision Tree; Mobile Telecommunications Services;

fLanguage

English

Publisher

ieee

Conference_Titel

Machine Learning and Cybernetics, 2008 International Conference on

Conference_Location

Kunming

Print_ISBN

978-1-4244-2095-7

Electronic_ISBN

978-1-4244-2096-4

Type

conf

DOI

10.1109/ICMLC.2008.4620698

Filename

4620698