Dereje, Gebremariam Kefena (2015) Discovery of Hidden Knowledge from Ethio Telecom Mobile Network Data. Masters thesis, Addis Ababa University.
![[img]](http://thesisbank.jhia.ac.ke/style/images/fileicons/application_pdf.png) |
PDF (Discovery of Hidden Knowledge from Ethio Telecom Mobile Network Data)
Dereje, Gebremariam.pdf - Accepted Version Restricted to Repository staff only Download (1MB) | Request a copy |
Abstract
The main aim of Telecommunications Companies is to deliver Quality of Service (QoS) to their customers. Currently, ethio telecom uses the traditional simple statistical method to analyze the data extracted from Mobile Network Management System database which is used to evaluate the performance of the network, Quality of the service as well as for decision making. We have seen that the result from this analysis is insufficient to give information for better decision making. This research was aimed to discover hidden knowledge from ethio telecom mobile network data. To overcome the drawback of simple statistical method we proposed data mining techniques, methods and methodologies and used in this research. In order to discover knowledge from the data we have used the divisive hierarchical clustering method to cluster the data. The k-means algorithm, Waikato Environment for Knowledge Analysis (WEKA) tool and CRISP data mining process model are used during this research work. Data preprocessing was done using different data mining methods to prepare the data for analysis. After data preprocessing we have found relevant attributes and clustering was conducted on the preprocessed data. During clustering, first we cluster the data set into two, then we further cluster those clusters contains dissimilar instances. Finally, we get clusters with similar behavior to analyze and interpret. As a result, we shown the knowledge which was discovered during analysis of each cluster and the relationship between attributes against CSSR. The data shows that most of the Call Setup are failed and categorized under Very Poor CSSR category. To enhance Call Setup Success Rate emphasize should be given to attributes used as KPIs. The research result reveals which attribute should enhance to improve the call setup success rate. Enhancing CSSR leads giving QoS to customers and it implies customer satisfaction and increases company revenue. Finally, we recommend ethio telecom to apply data mining technique using cluster analysis on GSM mobile network data to analyze the data, evaluate the performance of the network, to assess the quality of the service and to make better decision.
| Item Type: | Thesis (Masters) |
|---|---|
| Uncontrolled Keywords: | Data Mining, Knowledge discovery, GSM, QoS, Cluster Analysis, CRISP-DM, CSSR |
| Subjects: | Q Science > QA Mathematics > QA75 Electronic computers. Computer science Q Science > QA Mathematics > QA76 Computer software |
| Divisions: | Africana |
| Depositing User: | Selom Ghislain |
| Date Deposited: | 04 Oct 2018 08:14 |
| Last Modified: | 04 Oct 2018 08:14 |
| URI: | http://thesisbank.jhia.ac.ke/id/eprint/5882 |
Actions (login required)
 |
View Item |