Abstract
There is more than one mobile-phone subscription per member of the Australian population. The number of complaints against the mobile-phone-service providers is also high. Therefore, the mobile service providers are facing a huge challenge in retaining their customers. There are a number of existing models to analyse customer behaviour and switching patterns. A number of switching models may also exist within a large market. These models are often not useful due to the heterogeneous nature of the market. Therefore, in this study we use data mining techniques to let the data talk to help us discover switching patterns without requiring us to use any models and domain knowledge. We use a variety of decision tree and decision forest techniques on a real mobile-phone-usage dataset in order to demonstrate the effectiveness of data mining techniques in knowledge discovery. We report many interesting patterns, and discuss them from a brand-switching and marketing perspective, through which they are found to be very sensible and interesting.
| Original language | English |
|---|---|
| Pages (from-to) | 1-17 |
| Number of pages | 17 |
| Journal | Australasian Journal of Information Systems |
| Volume | 20 |
| DOIs | |
| Publication status | Published - 2016 |
Bibliographical note
Copyright the Author(s) 2016. Version archived for private and non-commercial use with the permission of the author/s and according to publisher conditions. For further rights please contact the publisher.Keywords
- decision tree
- decision forest
- ensemble of decision trees
- data mining
- brand switching
- switching behaviour