ABSTRACT
The challenges faced by telecommunication industries are many, there is need to eliminate or curb some of these challenges and that is when a decision support system comes into play. A decision support system (DSS) is one which can aid to strategize management within industries to make vital decisions in relation to customer and network data. This enables managers in their areas within their industries to fully utilize the amount of data available to make decisions in relation to utilization of valuable and important resources.
This research project therefore, focused on designing a fraud detection system with minimum false positive alerts using decision tree learning. The system has been trained to learn from training data and used decision tree algorithms to make predictions on future telecommunication data. Fraud detection is hard, so it is not surprising that many fraud systems have serious limitations. Different systems may be needed for different kinds of fraud with each system having different procedures, different parameters to tune, different database interface, different case management tools and features.
TABLE OF CONTENTS
| Title Page | …………………………………………………………… | i |
| Approval Page | ………………………………………………………….. | ii |
| Declaration | ……………………………………………………………. | iii |
| Dedication | …………………………………………………………….. | iv |
| Acknowledgement ………………………………………………………. | v | |
| Abstract | ……………………………………………………………… | vi |
Table of Contents …………………………………………………….. vii – ix
CHAPTER ONE – INTRODUCTION
- Background of the Study ………………………………………… 1-3
- Statement of General Problem …………………………………… 3-4
- Objective of the Study ………………………………………… 4
1.6 Definition of Terms ……………………………………………… 5
CHAPTER TWO – REVIEW OF RELATED LITERATURE
2.0 Introduction ………………………………………………………. 6
2.1.1 Call detail data ……………………………………………………. 7-9
2.1.2 Network data ………………………………………………………. 9
2.1.3 Customer data ……………………………………………………… 10
2.2.2 Customer churn ……………………………………………………… 12-13
2.3 Network unavailability ………………………………………………. 13
2.4 Tariffs ……………………………………………………………….. 13-14
2.5 Subscriber churning …………………………………………………… 15
2.6 Fraud detection ………………………………………………………. 15-16
2.7 Network fault isolation ………………………………………………. 16-18
2.8 Empirical review ……………………………………………………… 18-20
CHAPTER THREE – SYSTEM ANALYSIS AND DESIGN
3.1 Introduction ……………………………………………………… 21
3.2 Data preparation ………………………………………………. 21-22
3.3 System Design ……………………………………………………. 22-23
3.4 Monitoring and administration …………………………………… 23
3.5 ETLR ……………………………………………………………… 23-25
3.6 Data warehouse …………………………………………………… 26-27
3.7 Method of Data analysis …………………………………………… 27
3.8 Knowledge discovery ………………………………………………. 27-28
CHAPTER FOUR – IMPLEMENTATION, TESTING AND INTEGRATION
4.0 Choice of developing tools ………………………………….. 29
4.1 System requirement ………………………………………….. 29
- Software requirement…………………………………………………………………………. 29
- Hardware requirements……………………………………………………………………. 29
- System results………………………………………………………………………………… 31-35
CHAPTER FIVE – SUMMARY, CONCLUSION AND RECOMMENDATION
- Summary of findings………………………………………………………………….. 36
- Conclusion……………………………………………………………………………….. 36
- Recommendations…………………………………………………………………….. 36
References Appendix A
CHAPTER ONE
INTRODUCTION
A decision support system is a system with a graphic interface that allows interactive analysis of the different scenarios presented. The system contains a set of mathematical programming models and has the capability to dynamically construct and solve instances of those models. It also provides data presentation and reports. The system is an integrated, user friendly and a powerful tool to making planning studies by firms developing cable network systems in the telecommunication market.
BACKGROUND TO THE STUDY
(Han et al, 2012) The telecommunications industry generates and stores a tremendous amount of data. These data include call detail data, which describes the calls that traverse the telecommunication networks, network data, which describes the state of the hardware and software components in the network, and customer data, which describes the telecommunication customers (Roset et al, 2012). The amount of data is so great that manual analysis of the data is difficult, if not impossible. The need to handle such large volumes of data led to the development of knowledge-based expert systems. These automated systems perform important functions such as identifying fraudulent phone calls and identifying network faults. The problem with this approach is that it is time consuming to obtain the knowledge from human experts and, in many cases, the experts do not have the requisite knowledge. The advent of decision support system promise solutions to these problems and for this reason the telecommunications industry was an early adopter of decision support system.
Telecommunication data have several interesting issues for data mining. The first concerns scale, since telecommunication databases may contain billions of records and are amongst the
largest in the world. A second issue is that the raw data is often not suitable for data mining. For example, both call detail and network data are time-series data that represent individual events. Before this data can be effectively mined, useful summary features must be identified and then the data must be summarized using these features, because many data mining applications in the telecommunications industry involve predicting very rare events, such as the failure of a network element or an instance of telephone fraud, rarity is another issue that must be dealt with. The fourth and final data mining issue concerns real-time performance because many data mining applications, such as fraud detection, require that any learned model/rules be applied in real-time (Ezawa& Norton, 2015). Several techniques being applied is tackling all these issues in telecommunication companies.
Telecommunication networks are extremely complex configurations of equipment, comprised of thousands of interconnected components. Each network element is capable of generating error and status messages, which leads to a tremendous amount of network data. This data must be stored and analyzed in order to support network management functions, such as fault isolation/detection. This data will include a time stamp, a string that uniquely identifies the hardware or software component generating the message and a code that explains why the message is being generated. For example, such a message might indicate that “controller 1 experienced a loss of power for 40 seconds starting at 09:03am on Tuesday, June 13.”
Due to the large number of network messages generated, technicians cannot possibly handle every message. For this reason expert systems have been developed to automatically analyze these messages and take appropriate action, only involving a technician when a problem cannot be automatically resolved. This study is focused on AIRTEL NIGERIA.
Formally known as Celtel Nigeria, the company was established in 2000, by a group of institution and private investors as well as three state governments.
It made history on August 5, 2001 by becoming the first telecoms operator to launch commercial GSM services in Nigeria. In 2006, following Celtel International’s acquisition of majority stake in the company, it was re-branded Celtel and became an important part of Celtel’s pan-African operations spanning 14 countries. It was rebranded on August 1, 2008 from Celtel Nigeria to Airtel Nigeria following the global acquisition of Celtel International by Airtel Group.
Airtel Nigeria, which currently covers over 1500 towns and 14000 communities across the six geopolitical zones of the country, scored a series of many other “firsts” in the highly competitive Nigerian telecommunications market including the first to introduce toll-free 24- hour customer care line-111; they were the first to launch service in all the six geo-political zones in the country; also the first to introduce N500 recharge card; first to commence emergency service (Celtel 199); first to introduce monthly free SMS and first to introduce monthly airtime bonus.
STATEMENT OF THE PROBLEM
Due to findings fraud is a serious problem for telecommunication companies, leading to loss of billions of naira in revenue each year. Fraud is divided into two categories: subscription fraud and super imposition fraud. Subscription fraud is when a customer opens an account with the intention of not paying for the account charges. Super imposition fraud involves a legitimate account with some legitimate activity, but also includes some “super imposed” illegitimate activity by a person other than the account holder. Super imposition fraud poses a bigger threat for the telecommunications industry and for this reason data mining technique is used for identifying this type of fraud. These applications should ideally operate in real-time using the call detail records and, once fraud is detected or suspected, should trigger some action. This action may be to immediately block the call and/or deactivate the account, or may involve
opening an investigation, which will result in a call to the customer to verify the legitimacy of the account activity. However, this study will examine various data mining techniques of telecommunication companies in Nigeria.
