"Predicting Customer Churn in the Mobile Telecommunication Industry, a Case Study of MTN Ghana, Kumasi"
| dc.contributor.author | Abiw-Abaidoo Jnr, Kojo | |
| dc.date.accessioned | 2012-07-20T10:39:01Z | |
| dc.date.accessioned | 2023-04-19T18:11:45Z | |
| dc.date.available | 2012-07-20T10:39:01Z | |
| dc.date.available | 2023-04-19T18:11:45Z | |
| dc.date.issued | 2011-10-20 | |
| dc.description | A Thesis submitted to the Institute of Distance Learning, Kwame Nkrumah University of Science and Technology in partial fulfillment of the requirements for the degree of Commonwealth Executive Masters of Business Administration, October, 2011 | en_US |
| dc.description.abstract | Customer churn has been of much concern for companies, very active in industries where lower switching cost exists. The Telecommunication Industry is among those industries which suffer from this phenomenon, producing an annual churn rate of 30%. The best way to handle this is to understand the behavior and trend of those who churn so as to be always ahead of them. MTN Ghana, Kumasi was used as a case study to develop a predictive model for the prepaid telephony segment. The objectives of this study were to find out the extent of customer churn in MTN Ghana, Kumasi, the causes and effects of customer churn and to develop a predictive model for churn in the telecommunication industry. Questionnaires were used to find the causes of churn from the customer‘s perspective. An already defined churn variable dataset of 3333 records was used for the Predictive Model with Data Mining Techniques. The monthly churn rate for the industry is 2.5%. Poor network quality, high call charges, poor customer service and promotions from competitors are the major causes of churn. Even with the low churn rate the effects on the telecommunication firms are serious; Churn affects Market share, frustrates effort to achieve projected revenue, dissatisfied customers dent the brand image, increases operational costs as it requires marketing intervention to win-back churners as well as potential churners. Developing the predictive model, the neural network was used to calculate the propensity for a customer in the dataset to churn while the decision tree describes the behavior of the churners. The propensity for a customer to churn is 1.03 times, customer service calls, day call and international calls were the major characteristics exhibited by the churners. | |
| dc.description.sponsorship | KNUST | en_US |
| dc.identifier.uri | https://ir.knust.edu.gh/handle/123456789/4431 | |
| dc.language.iso | en | en_US |
| dc.title | "Predicting Customer Churn in the Mobile Telecommunication Industry, a Case Study of MTN Ghana, Kumasi" | en_US |
| dc.type | Thesis | en_US |
Files
Original bundle
1 - 1 of 1
Loading...
- Name:
- Kojo Abiw-Abaidoo.pdf
- Size:
- 911.82 KB
- Format:
- Adobe Portable Document Format
- Description:
- Full Thesis