case study of data mining in telecommunications

Data Mining Methods, Models and Solutions for Big Data Cases in Telecommunication Industry

• Conference paper
• First Online: 23 July 2021
• Cite this conference paper

• Nataliia Kuznietsova   ORCID: orcid.org/0000-0002-1662-1974 4 ,
• Peter Bidyuk   ORCID: orcid.org/0000-0002-7421-3565 4 &
• Maryna Kuznietsova   ORCID: orcid.org/0000-0001-6054-418X 5  

Part of the book series: Lecture Notes on Data Engineering and Communications Technologies ((LNDECT,volume 77))

Included in the following conference series:

• International Scientific Conference “Intellectual Systems of Decision Making and Problem of Computational Intelligence”

660 Accesses

3 Citations

This paper is concentrated on the applications of main data mining tools, methods, models and technologies for solving the basic tasks of data processing for telecommunication industry. The main forecasting task in this industry is to predict the class and volume of services needed for the subscribers as well as for predicting the capacity of all needed engineering equipment. It is proposed to develop regression and forecasting models based upon the Facebook Prophet module to take into account seasonal effects in data and to compare the results with the ones received by using the LSTM network. The classification task was related to the problem of churn prediction. The authors identified such promising methods as decision trees, random forest, logistic regression, neural networks, support vector machines and gradient boosting to solve problems of subscribers classification by their certain preferences and services, as well as the tendency to outflow. The dynamic approach based on dynamic models of survival theory for churn time prediction is proposed. Next the task of forecasting the volume and class of services which subscribers are going to use in roaming is solved. The results of using regression models and data mining methods were also shown. All the methods proposed were compared and evaluated by necessary statistical characteristics, and interpretation of the model application results for practical solutions were proposed. Finally in the paper the client-service information technology with all needed functionality for solving all these tasks is proposed.

• Data mining
• Churn prediction
• Regression models
• Facebook Prophet
• Gradient boosting
• LSTM network
• Dynamic risk assessment
• Mobile Internet
• Telecommunication company

This is a preview of subscription content, log in via an institution to check access.

Access this chapter

• Available as PDF
• Read on any device
• Instant download
• Own it forever
• Available as EPUB and PDF
• Compact, lightweight edition
• Dispatched in 3 to 5 business days
• Free shipping worldwide - see info

Tax calculation will be finalised at checkout

Purchases are for personal use only

Institutional subscriptions

Ministry of digital transformation of Ukraine (2021). https://thedigital.gov.ua/news/mintsifra-bilshe-126-tis-ukraintsiv-otrimali-4g-vpershe-v-lyutomu

Beran, J.: Mathematical Foundations of Time Series Analysis, p. 309. Springer, Cham (2017). https://doi.org/10.1007/978-3-319-74380-6

Brandusoiu, I., Toderean, G.: Predicting churn in mobile telecommunications industry. Electron. Telecommun. 51 , 1–6 (2010)

Google Scholar  

Breiman, L.: Random forests. Mach. Learn. 45 , 5–32 (2001). https://doi.org/10.1023/A:1010933404324

Article   MATH   Google Scholar  

Brownlee, J.: How to develop LSTM models for time series forecasting (2018). https://machinelearningmastery.com/how-to-develop-lstm-models-for-time-series-forecasting/

Chih-Ping, W., I-Tang, C.: Turning telecommunications call details to churn prediction: a data mining approach. Expert Syst. Appl. 23 (1), 103–112 (2002). https://doi.org/10.1016/S09574174(02)000301

Chistyakov, S.: Random forests: an overview. Works of Karelian scientist center of RAS 1 , 117–136 (2013). (in Russian)

Cortes, C., Vapnik, V.: Support-vector networks. Mach. Learn. 20 (3), 273–297 (1995). https://doi.org/10.1007/BF00994018

Coussement, K., Poel, D.: Churn prediction in subscription services: an application of support vector machines while comparing two parameter-selection techniques. Expert Syst. Appl. 34 , 313–327 (2008)

Article   Google Scholar  

Friedman, J.H.: Greedy function approximation: a gradient boosting machine. Ann. Stat. 29 (5), 1189–1232 (2001). http://www.jstor.org/stable/2699986

Hanzo, L., Akhtman, Y., Wang, L., Jiang, M.: MIMO-OFDM for LTE, WiFi and WiMAX: Coherent Versus Non-Coherent and Cooperative Turbo Transceivers, p. 692. Wiley-IEEE Press (2020)

Havrylovych M., Kuznietsova, N.: Survival analysis methods for churn prevention in telecommunications industry. In: CEUR Workshop Proceeding, vol. 2577, pp. 47–58. CEUR (2020). http://ceur-ws.org/Vol-2577/paper5.pdf

Herrera, F., Charte, F., Rivera, A., Jesus, M.: Multilabel Classification. Problem Analysis, Metrics and Techniques, p. 194. Springer, Cham (2016). https://doi.org/10.1007/978-3-319-41111-8

Hung, S., Yen, D., Wang, H.: Applying data mining to telecom churn management. Expert Syst. Appl. 31 , 515–524 (2004)

Kuznietsova, N., Bidyuk, P.: Intelligence information technologies for financial data processing in risk management. In: Babichev, S., Peleshko, D., Vynokurova, O. (eds.) Data Stream Mining & Processing. Communications in Computer and Information Science, vol. 1158, pp. 539–558 (2020). https://doi.org/10.1007/978-3-030-61656-4_36

Kuznietsova, N., Kuznietsova, M.: Data mining methods application for increasing the data storage systems fault-tolerance. In: 2020 IEEE 2nd International Conference on System Analysis & Intelligent Computing (SAIC), pp. 315–318 (2020). https://doi.org/10.1109/SAIC51296.2020.9239222

Kuznietsova, N.V.: Information technologies for clients’ database analysis and behaviour forecasting. In: CEUR Workshop Proceeding, vol. 2067, pp. 56–62. CEUR (2017). http://ceur-ws.org/Vol-2067/

Kuznietsova, N.V.: Dynamic method of risk assessment in financial management system. Registration Storage Data Process. 21 (3), 85–98 (2019). https://doi.org/10.35681/1560-9189.2019.21.3.183724

Kuznietsova, N.V., Bidyuk, P.I.: Dynamic modeling of financial risks. Inductive Model. Complex Syst. 9 , 122–137 (2017). http://nbuv.gov.ua/UJRN/Imss_2017_9_15

Kuznietsova, N.V., Bidyuk, P.I.: Modeling of financial risk in the telecommunications field. Sci. News NTUU “KPI” 5 , 51–58 (2017). https://doi.org/10.20535/1810-0546.2017.5.110338

Kwiatkowski, D., Phillips, P., Schmidt, P., Shin, Y.: Testing the null hypothesis of stationarity against the alternative of a unit root: how sure are we that economic time series are nonstationary? J. Econ. 54 , 159–178 (1992)

Mozer, M.C., Wolniewicz, R., Grimes, D.B., Johnson, E., Kaushansky, H.: Predicting subscriber dissatisfaction and improving retention in the wireless telecommunications industry. IEEE Trans. Neural Networks 11 (3), 690–696 (2000). https://doi.org/10.1109/72.846740

Nikulin, V.N., Kanishchev, I.S., Bagaev, I.: Methods of balancing and normalization of data to improve the quality of classification. Comput. Tools Educ. 3 , 16–24 (2016)

Orac, R.: LSTM for time series prediction (2019). https://towardsdatascience.com/lstm-for-time-series-prediction-de8aeb26f2ca

Osovsky, S.: Neural networks for information processing (translation in Russian by I.D. Rudinsky), p. 344. Finance and statistics (2002)

Papageorgiou, N.S., Radulescu, V.D., Repovs, D.D.: Nonlinear Analysis – Theory and Methods, p. 586. Springer, Cham (2019). https://doi.org/10.1007/978-3-030-03430-6

Robson, W.: The math of Prophet (2019). https://medium.com/future-vision/the-math-of-prophet-46864fa9c55a

Taylor, S., Letham, B.: Forecasting at scale. PeerJ Preprints 5 , 1–25, e3190v2 (2017). https://doi.org/10.7287/peerj.preprints.3190v2

Tsay, R.: Analysis of Financial Time Series, p. 720. Wiley, New York (2010)

Book   Google Scholar  

Umayaparvathi, V., Iyakutti, K.: Applications of data mining techniques in telecom churn prediction. Int. J. Comput. Appl. 42 , 5–9 (2012). https://doi.org/10.5120/5814-8122

Download references

Author information

Authors and affiliations.

Institute for Applied System Analysis of the National Technical University of Ukraine “Igor Sikorsky Kyiv Polytechnic Institute”, Kyiv, Ukraine

Nataliia Kuznietsova & Peter Bidyuk

Institute for Information Recording of the National Academy of Sciences of Ukraine, Kyiv, Ukraine

Maryna Kuznietsova

You can also search for this author in PubMed   Google Scholar

Corresponding author

Correspondence to Nataliia Kuznietsova .

Editor information

Editors and affiliations.

Department of Physics, Kherson State University, Kherson, Ukraine

Sergii Babichev

Department of Informatics and Computer Science, Kherson National Technical University, Kherson, Ukraine

Volodymyr Lytvynenko

Rights and permissions

Reprints and permissions

Copyright information

© 2022 The Author(s), under exclusive license to Springer Nature Switzerland AG

About this paper

Cite this paper.

Kuznietsova, N., Bidyuk, P., Kuznietsova, M. (2022). Data Mining Methods, Models and Solutions for Big Data Cases in Telecommunication Industry. In: Babichev, S., Lytvynenko, V. (eds) Lecture Notes in Computational Intelligence and Decision Making. ISDMCI 2021. Lecture Notes on Data Engineering and Communications Technologies, vol 77. Springer, Cham. https://doi.org/10.1007/978-3-030-82014-5_8

Download citation

DOI : https://doi.org/10.1007/978-3-030-82014-5_8

Published : 23 July 2021

Publisher Name : Springer, Cham

Print ISBN : 978-3-030-82013-8

Online ISBN : 978-3-030-82014-5

eBook Packages : Intelligent Technologies and Robotics Intelligent Technologies and Robotics (R0)

Share this paper

Anyone you share the following link with will be able to read this content:

Sorry, a shareable link is not currently available for this article.

Provided by the Springer Nature SharedIt content-sharing initiative

• Publish with us

Policies and ethics

• Find a journal
• Track your research

• Trending Now
• Foundational Courses
• Data Science
• Practice Problem
• Machine Learning
• System Design
• DevOps Tutorial
• Data Mining - Cluster Analysis
• Aggregation in Data Mining
• Data Mining For Intrusion Detection and Prevention
• Privacy, security and social impacts of Data Mining
• Difference Between Classification and Prediction methods in Data Mining
• Data Mining and Recommender Systems
• Data Mining Query Language
• Python - Gaussian fit
• What is a DNS Amplification Attack?
• What’s a broadcast storm?
• What is Network Segmentation?
• What is Data Masking?
• Transitioning to x64 Architecture in Android
• How to Check the Visibility of Software Keyboard in Android?
• How to Select Words With Certain Values at the End of Word in SQL?
• Sharing Shortcuts in Android
• Introduction to Visual Programming Language
• Overview of SNMPv3
• How to Compile, Decompile and Run C# Code in Linux?

Data Mining for Retail and Telecommunication Industries

Data Mining plays a major role in segregating useful data from a heap of big data. By analyzing the patterns and peculiarities, it enables us to find the relationship between data sets. When the unprocessed raw data is processed into useful information, it can be applied to enhance the growth of many fields we depend on in our day-to-day life.

This article shows the data mining role in the retail and telecommunication industries.

Role of data mining in retail industries

In the dynamic and fast-growing retail industry, the consumption of goods increases day by day which in turn increases the data collected and used. The retail industry includes the sales of goods to the customer through retailers. It covers from a local booth in the street to the big malls in cities. For eg: The grocery shop owner in a defined area would know about their customer details after-sales for few months. When he notes the need of his customer, it would be easy to enhance the sales. The same happens in the big retail industries. They collect customers’ responses to a product, the time zone, their location, shopping cart history, etc. Preference of brands and products help the company to create targeted ad to increase the sales and profit.

Knowing the customers:

What is the purpose of sales if the retailer doesn’t know who their customers are? It’s a definite need to understand about their customers. It starts by analyzing them with various factors. Finding the source by which the customer gets to know about that retailing platform would help in enhancing the advertisement of retailers to attract a completely new set of people. By finding the days they have frequently purchased can help in discount sales or special boost up on festival days. The time they spend buying per order can give us useful statistical data to enhance growth. The amount of money spent on the order can help the retailer in separating the customer crowd into groups of High paid orders, medium-paid orders, and low-paid orders. This will increase the targeted customers or help in introducing customized packages depending on price. By knowing the language and payment method preferences, retailers can provide required services to satisfy the customers. Managing a good business relationship with the customer can gain trust and loyalty that can bring a rapid profit for the retailer. The retention of customers in their company will help them to withstand the competition between similar other companies.

RFM stands for Recency, Frequency, Monetary value . Recency is nothing but the nearest or recent time when the customer made a purchase. Frequency is how often the purchase had taken place and Monetary value is the amount spent by the customers on the purchase. RFM can surge monetization by holding on to the regular and potential customers by keeping them happy with satisfying results. It can also help in pulling back the trailing customers who tend to reduce the purchase. The more the RFM score, the more the growth of sales is. RFM also prevents from sending over requests to engaged customers and it helps to implement new marketing techniques to low ordering customers. RFM helps in identifying innovative solutions.

Market-based analysis:

The market-based analysis is a technique used to study and analyze the shopping sequence of a customer to increase revenue/sales. This is done by analyzing datasets of a particular customer by learning their shopping history, frequently bought items, items grouped like a combination to use.

A very good example is the loyalty card issued by the retailer to customers. From the customer’s point of view, the card is needed to keep track of discounts in the future, incentive criteria details, and the history of transactions. But, if we take this loyalty card from a retailer point of view, the applications of market-based analysis will be layered inside to collect the details about the transaction.  

This analysis can be achieved with data science techniques or various algorithms. This can even be achieved without technical skills. Microsoft Excel platform is used to analyze the customer purchases, frequently bought or frequently grouped items. The spreadsheets can be organized by using ID as specified for different transactions. This analysis helps in suggesting products for the customer which may pair well with their current purchase which leads to cross-selling and improved profits. It also helps to track the purchase rate per month or year. It manifests the correct time for the retailer to make the desired offers to attract the right customers for the targeted products.

Potent sales campaign:

Everything nowadays needs advertising. Because advertising the product helps people know about its existence, use, and features. It takes the product from the warehouse to the real world. If it has to attract the right customers, data must be analyzed. This is the right call to sales or market campaign performed by the retailers. The marketing campaigns must be initiated with the right plans else it may lead to loss of company by over-investing in untargeted Advertisements. The sales campaign depends on the time, location, and preference of the customer. The platform in which the campaign takes place also plays a major role in pulling the right customers in. It requires regular analysis of the sales and its associated data taking place in a particular platform at a certain time. The traffic in social or network platforms will give us the favoring of campaigned product or not. The retailer can make changes in the campaign with the previous statistics which rapidly increases the sales profit and prevents overspending. Learning about the customer profits and the company profits can enhance the usage of campaigns. The number of sales per one campaign can also guide the retailer on whether to invest in it or not. A trial-and-error method can be converted into a well-transformed method by the efficient handling of data. A multi-channel sale campaign also helps to analyze the purchases and surges the revenue, profit, and number of customers.

Role of data mining in telecommunication industries

In the highly evolving and competitive surroundings, the telecommunication industry plays a major in handling huge data sets of customers, network and call data. To thrive in such an environment, the Telecommunication Industry must find a way to handle data easily. Data Mining is preferred to enhance the business and to solve the problem in this industry. The major function includes fraud call identification and spotting the defects in a network to isolate the faults. Data mining can also enhance effective marketing techniques. Anyways, this industry confronts challenges in dealing with the logical and time aspect in data mining which calls the need to foresee rarity in telecommunication data to detect network faults or buyer frauds in real-time.

Call detail data:

Whenever a call starts in the telecommunication network, the details of the call are recorded. The date and instant of time in which it happens, the duration of call along with the time when it ends. Since all the data of a call is collected in real-time, it is ready to be processed with data mining techniques. But we should segregate data from the customer level not from isolated single phone call levels. Thus, by efficient extraction of data, one can find the customer calling pattern.  

Some of the data that help to find the pattern are

• average time duration of calls
• Time in which the call took place (Daytime/Night-time)
• The average number of calls on weekdays
• Calls generated with varied area code
• Calls generated per day, etc.

By sensing the proper customer call details, one can progress the business growth. If a customer makes more calls during dayshift working hours, that makes them distinguished as a part of a business firm. If the night-time call rate is high, it may be used only for residential or domestic purposes. By the frequent variance in the area code, one can segregate the business calls because people calling for the residential purpose may call over limited area codes in a period. But the data collected in the evening time cannot give the exact detail of whether the customer belongs to a business or residential firm.

Data of customers:

When it comes to the telecommunication industry, there would be an enormous number of customers. This customer database is sustained for any further queries in the data mining process. For example, when a customer fraud case is encountered, these customer details would help in the identification of the person with the details in the customer database like name, address of the person. It would be easy to trace them and solve the issue. This dataset can also be extracted from external sources because mostly this information would be common. It also includes the plan chosen for subscription, proper payment history. By using this dataset, we can escalate the growth in telecommunication industries.

Network Data:

Due to the use of well-developed complex appliances used in telecommunication networks, there is a possibility that every part of the system may generate errors and messages. This leads to a large amount of network data being processed. This data must be separated, grouped, and stored in order if the system causes any network fault isolation . This ensures that the error or status message of any part of the network system would reach the technical specialist. So, they could rectify it. Since the database is enormous, when a large number of status or error messages get generated, it becomes difficult to solve the problems manually. So, some sets of errors and messages can be automatized to reduce the strain. A methodical approach of data mining can manage the network system efficiently which can enhance the functions.

Preparing and clustering data:

Even though raw data are processed in data mining, it must be in a well sensed and properly arranged format to be processed. And, in the telecommunication industry dealing with the giant database, it’s an important need. First, clashing and contrary data must be identified to avoid inconsistency. Making sure of the removal of undesired data fields heaping space. The data must be organized and mapped by finding the relationship between datasets to avoid redundancy.  

Clustering or grouping similar data can be done by algorithms in the data mining field. It can help in analyzing the patterns like calling patterns or customer behavior patterns. Group of frequencies is made by analyzing the similarities between them. By doing this, data can easily be understood which leads to easy manipulation and use.

Customer profiling:

The telecommunication industry deals with a large scale of customer details. It starts observing patterns of the customer from call data to profile the customers to predict future trends. By knowing the customer pattern, the company can decide the promotion methods offered to the customer. If the call ranges within an area code. The promotion made in that aspect would gain a group of customers. This can efficiently monetize the promotion techniques and stop the company from investing in a single subscriber but it can attract a group of people with the right plan. Privacy issues arise when the customer’s call history or details are monitored.

One of the significant problems that the telecommunication industry faces is that Customer churn . This can also be stated as customer turnover in which the company loses its client. In this case, the client leaves and switches to another telecommunication company. If the customer churn rate is high in a company, the respective company will experience severe loss of revenue and profit which will lead to its decline in growth. This issue can be fixed by data mining techniques to collect patterns of customers and profiling them. Incentive offers provided by companies attract the regular user of some other company. By profiling the data, the customer churn can be effectively forecasted by their behaviors like subscription history, the plan they choose, and so on. While collecting data from the paid customers, it’s also possible to collect data of the receiver or non-customer but with a set of restrictions.

Fraud detection:

Fraud is a critical problem for telecommunication industries which causes loss of revenue and also causes a deterioration in customer relations. Two major fraud activity involved is subscription theft and super-imposed frauds . The subscription fraud involves collecting the details of customers mostly from the KYC(Know Your Customer) documents like name, address, and ID proof details. These details are needed to sign up for telecom services with authenticating approval but without any type of intention to pay for using the service using the account. Some offender not only stops with the illegitimate use of services but perform bypass fraud by diverting voice traffic from local to international protocols which causes destructive loss to the telecommunication company. In super-imposed frauds, it starts with a legitimate account and a legal activity but with further lead to the overlapped or imposed activity by some other person illegally using the services rather than the account holder. But by collecting the behavioral pattern of the account holder, if a suspect is found on super-imposed fraudulent activities it will lead to immediate actions like blocking or deactivating the account user. This will prevent further damage to the company.

These fraudulent activities can be reduced by using data mining techniques to collect information of the customer and patterning their behavior like call details as said earlier can lead to the detection of frauds. When the data detection is performed in real-time, the frauds can easily be identified. This can also be done by comparing the account of suspected call behavior with the general fraud profiles. If the call pattern matches that of generic frauds, they can be detected. Instead of collecting data at the individual user level, collecting data from the customer level can enhance this fraud detection process. Sometimes the wrong classification of frauds may cause loss to the company. So, they must know the relative price of letting go of a false call and blocking a suspect for fraudulent activities with a legal account. The correct use of data mining would help in dealing with this issue with accuracy.

Please Login to comment...

Similar reads.

• Blogathon-2021
• data mining
• Data Mining
• CBSE Exam Format Changed for Class 11-12: Focus On Concept Application Questions
• 10 Best Waze Alternatives in 2024 (Free)
• 10 Best Squarespace Alternatives in 2024 (Free)
• Top 10 Owler Alternatives & Competitors in 2024
• 30 OOPs Interview Questions and Answers (2024)

Improve your Coding Skills with Practice

What kind of Experience do you want to share?

International Journal of Academic Research in Business and Social Sciences 2017, Vol. 7, No. 12 ISSN: 2222-6990

Business Intelligence Using Data Mining for Organizational Sustainability: A Case Study of Digi Telecommunication Sdn Bhd

Mohd Arif Fahmi Bidin, Alwi Mohd Yunus Faculty of Information Management, University Technology of Mara, UiTM Selangor, Malaysia

DOI: 10.6007/IJARBSS/v7-i12/3628 URL: http://dx.doi.org/10.6007/IJARBSS/v7-i12/3628

Abstract In today business, meeting consumer satisfaction and needs is an unquestionable requirement. The organizations need to incorporate the vast volumes of data accessible and to utilize this information to bolster the nature of their decision making, in order to remain competitive advantage (sustainability) and to expand the profit. This paper displays a log information explanatory process in telecommunication industry, for business intelligence intrigued by breaking down client and behavioural data to enhance their comprehension of client dependability and client’s satisfaction. The data mining procedure to accomplish key client management goals is introduced. This paper gives a demonstrated information explanatory strategy used to recognize variety kinds of attributes in telecommunication industry, specifically in Digi Telecommunication Sdn. Bhd, Malaysia. Keywords: Business Intelligence, Data Mining, Telecommunication Industry.

Introduction The organizations are becoming more and more cognizant about the importance and advantages of data and information kept in their organization. In order to stay competitive and remains sustain in business world, telecommunications company has to capture the right information at the right time and utilize that information to create profit and achieving customer satisfaction. In the 21st century, associations are developing into new structures in view of knowledge and networks in light of a turbulent and obscure condition characterized by indistinct organizational boundaries and fast- paced change (Seufert and Schiefer, 2005; Drucker, 1993; Kelly, 1998; Grove, 1999). In such conditions, information based resources are acknowledged to be the base of practical upper hand and the establishment of achievement in this century (Wiig 1997; Ross et al., 1996; Groom and David, 2001).

Fortunately, telecommunications companies know more about their customer than anyone else. With the help of Business Intelligence (BI) techniques, the telecommunication companies can easily tracking theirs customers’ activities and data. The organization have to extract and integrate large volume of data available for the quality of the decision– making and to improve customer relationship in order to increase profit and sustainability. One of the part of Business Intelligence (BI), data mining is the process of automatically discovering useful information in large data repositories (Tan, Steinbach and Kumar, 2006). Business intelligence (data mining) techniques are used to turn business data into valuable information and generate business intelligence, helping organizations to make effective

471 International Journal of Academic Research in Business and Social Sciences 2017, Vol. 7, No. 12 ISSN: 2222-6990 decisions. Data mining can be applied or nurture to any kind of business in any field, but this paper will describe why it is valuable to the telecommunication industry. One telecommunication company in Malaysia, Digi Telecommunication Sdn. Bhd. is an example of large organization actively performing business intelligence (BI) coupled with data mining for their sustainability.

Literature Review Business Intelligence Business Intelligence (BI) is data- driven decision making. According to Negash and Gray, 2006, Business Intelligence consolidates data gathering, information stockpiling, and knowledge management with systematic and analytical tools in order to present complex and complete information to the organization’s stakeholders and decision makers. In the making of the better and accurate decisions, every procedures and process in BI must been includes to bolster data gathering, sharing and reporting, however BI not entirely technological. As indicated by Castellanosm and Dayal, 2008, Business Intelligence (BI) includes the integration of core data with important business information to distinguish huge events, discover the new business situations and foresee business circumstances. BI incorporates the generation, aggregation, analysis, and visualization of data to illuminate and encourage business administration and strategizing. BI is top of the information and not exactly just how the data is assembled or crunched, yet BI is the thing that the business pioneers and top administrations really do with the insights information and decisions they gather from it. Turban, et al., 2002, defined BI as a computer based decision analysis normally done online by administrators and managers. It incorporates gauging, examining options and assessing danger (risk) and execution.

McLeod and Schell, 2001, contend that BI is an expansion of competitive intelligence (CI). Competitive intelligence (CI) involves investigating the business environment to impact its emerging technique for business improvement. It is characterized as significant proposals emerging from a precise procedure, including arranging, assembling, examining and scattering data on the external environment, for circumstances or advancements that can possibly influence an organization or a country’s competitive situation.

Furthermore, McLeod and Schell, 2001, aggressive global competition has constrained organizations to re-evaluate the path in which they accumulate information. Today, the gathering, storage and dissemination of environmental information represent an important computer application in many organizations around the globe. Initially, the application was devoted to gather information on the competitors and in this way the term competitive intelligence was instituted. At the point when characterized extensively to incorporate data on every single natural component, the best possible term is Business Intelligence (BI).

The way of characterizing BI is extremely complex. In any case, it can be reasoned that BI is a kind of decision support system (DSS). According to Rob and Coronel, 2002, DSS help the management of the organization in making the managerial decisions with the assistance of extensive data ‘massaging” usage in order to produce the information.

472 International Journal of Academic Research in Business and Social Sciences 2017, Vol. 7, No. 12 ISSN: 2222-6990

In this way, BI improves productivity in the telecommunication industry and can help administration to define methodologies, bolster decision making, foresee for circumstances, recognize issues or problems and substantiate activities. The utilization of expert systems such as Customer Relationship Management (CRM) system, it demonstrates the prevalence of data mining in the telecommunication industry these days.

Data Mining Discovering answers you didn't have any acquaintance with you were searching for in advance is the thing that Data Mining is about. With so much data accessible, you can never make sure you're not ignoring some key certainty indicating the way better execution. Data mining is the act of filtering through all the proof looking for already unrecognized examples. A few organizations are notwithstanding procuring Data Scientists, specialists in insights and software engineering who know every one of the traps for finding the signs covered up in the clamour. Data mining likely fits inside the classification of investigation, however most examination depends on information from frameworks set up to track known KPIs—so it's generally more measuring than mining. Data mining; where the data is prepared under measurable based calculations or algorithms, which could retrieve useful information from it.

Managing the centrality of large amount of data, rather than single information, is an exceptionally recognizable activities to each type of human knowledge. In that way, utilizing statics as reason for data analysis turns out to be increasingly important for creating productive and supportive knowledge in business. Data mining is the way of applying rational analytical process - statical techniques - to measure of data in order to make merged patterns. Data mining exploits computational capacity to plunge further in meaning of patterns than immaculate statics. At the point when aligned with an information distribution centre stockpiling ability and the ideas of BI, data mining can provide for a business or organization, accuracy and security while making decisions. Vast amount of data, for example the customers’ profile of a major organization, would be practically difficult to extract reasonable information without the assistance of precise strategies and procedures. Understanding the dimensions of issues like these, insightful managing this data requests appropriate data mining processes. In the real business setting, data mining procedure can be separated into four principal stages: • Classification: Is the part which crude information must be isolated into gatherings, keeping in mind the end goal to isolate the common examples (the noticeable ones). • Clustering: With the assistance of innovation and particular hierarchical strategies, information is figured out how to make littler gatherings (less noticeable to human's eyes). • Statistical fitting: In this stage, is hunt down knowing scientific examples in information qualities. • Association: Useful data regularly agree numerous factors, which bonds can be found in affiliation forms.

473 International Journal of Academic Research in Business and Social Sciences 2017, Vol. 7, No. 12 ISSN: 2222-6990

Telecommunications Industry in Malaysia Telecommunication industry in Malaysia has entered a very competitive for as far back as couple of decades. According to Mazlan, 2005, the end of monopoly by the telecommunication services since 1992 is one of the top priorities made by the government of Malaysia in order to become the developed country in 2020. The extension and improvement of telecommunication services are imperative for the development of country. The initial step included the joining of Telekom Malaysia in 1987 as a government- owned company. Afterward, new telecommunication companies were authorized to provide certain services, for example, mobile cell phones, pagers, trunked radio, two-way radio systems and other services, according to The National Media transmission Policy of Malaysia (NTP), 1994. Mohamad, 2004 believes that the development in Malaysia's telecommunication sectors will be fuelled by more prominent customer enthusiasm for rapid broadband Internet. The government has had its influence in this improvement through its National Broadband Plan. Rapid development of the internet and information technology sector has made telecommunications companies into a new competitive business environment. According to Chong et al., 2006, Malaysia’s telecommunications company need to be proactive in driving and transforming the Malaysian economy into a knowledge- based economy (K- Economy).The integration between the telecommunications and IT industries additionally brings the rapid development of complex innovation, which introduces a new information technology- based century. Malaysian Communications and Multimedia Commission in 2007 reported that there were five telecommunication services companies in Malaysia to provide services for 26 million populations.

(1) Telekom Malaysia Berhad (TM Bhd) - a large government-linked company, (2) MAXIS Mobile Berhad (MAXIS), (3) Celcom Berhad, (4) Time Telecommunications, large locally-owned private companies, and (5) DIGI Communication Bhd – multinational company.

These organizations are competing for market share of 4.60 million fixed line telephone services, 11.43 million services and 2.89 million dial-up internet clients (Malaysian Correspondence and Multimedia Commission, 2008). The competition among these companies are stiff in order to attract the customers and remain sustain. The existing customers as well the potential customers were promoted to the services provided via advertisements such as billboards, brochures, campaigns and through social media platforms. Various benefits and incentives for example, price reduction, flexible services and attractive packages were offered to the customers to join or switch into their plans.

Links between Data Mining, BI, and Knowledge Management Distinction between BI and KM Cook and Cook, 2000, stated that BI is the uses of applications and technologies to capture, access, and analyse the vast amount of data processes into useful information for the organization or management to make effective business decisions. This statement also supported by Williams and Williams in 2006. Loshin,2003, believes the basic technologies of BI which includes business rule modelling, data warehousing, data

474 International Journal of Academic Research in Business and Social Sciences 2017, Vol. 7, No. 12 ISSN: 2222-6990 profiling and online analytical processing also data mining, fully utilized and integrated massive data to help the organization gain competitive advantages. Meanwhile, Knowledge Management (KM) is a set of practices of creation, development and application of knowledge to enhance and increase the organization’s performance, cited by Wiig, 1999; Buckman, 2004; Feng and Chen, 2007; Lee and Change, 2007; Smoliar, 2007; Wu et al., 2007; Paiva and Goncalo, 2008; Ramachandran et al., 2008. KM improves the knowledge and information usage in organization, similarly to BI, yet different in many aspects. KM is more focusing to human subjective knowledge, not data or objective information. According to Nonaka and Takeuchi, 1995, majority of models in KM such as tacit and explicit knowledge framework are purposely used for a dynamic human process to justify personal belief and truth; which are basically non-technology oriented.

Data Mining is a bond between BI and KM Data mining (DM) is known as a powerful BI tool for knowledge discovery. Brachman et al., 1996, sees the process of DM is a KM process because of the involvement of human knowledge. Data mining can be valuable for KM in two ways:

1. To share mutual understanding of BI context among the data miners and analyst. 2. The practices and usages of DM tools to extend human knowledge.

The integration of DM and KM can be found at the conceptual level. Malhotra, 2004 proposed the integration models between KM and DM for routine structured information processing and non- routine unstructured sense making. In addition, White, 2005, provides a flowchart model on the use of BI in the KM for decision making process which includes the involvement, collaboration and integration between knowledge workers and knowledge managers in socialization.

Methodology The case study examines a Customer Relationship Management (CRM) system developed and implemented by Digi Telecommunication Sdn. Bhd., a telecommunication company in Malaysia. CRM empowers the information accumulation over the clients profile and lessen the operational cost. CRM turns into an indispensable part to the development of the data mining keeping and the end goal is to bolster association applications and business insight capacities. A definitive objective is to catch and order the information on clients from different stages – email, site, live visit, phone discussion and online networking input from the present and potential clients. All the data will be processes and analyses to produce useful information for the management in making the decisions.

This case study is based on in- depth interviews with the management of Digi Telecommunication Sdn. Bhd., alongside the optional information gotten to from multi- sources, for example, Digi's sites, Digi's yearly journals and reports. The main fieldwork was conducted with semi-structured interviews of the most knowledgeable manager and informant at Digi’s corporate headquarter. The scope of the meetings shrouded many variables required in the improvement and usage procedure of the CRM framework. Documentary evidence permitted cross-checking of much of the interview materials. The utilization of remotely situated articles gave yet another strategy to triangulate the

475 International Journal of Academic Research in Business and Social Sciences 2017, Vol. 7, No. 12 ISSN: 2222-6990 legitimacy of the meeting data In addition, the document and interview data were transcribes, investigated and triangulated with iterative confirmation with interviewee until organized discoveries were shaped. Given the nature and contextual conditions of CRM system, the report of this case study is qualitative.

Findings Organization Background Digi Telecommunications Sdn Bhd is a telecommunications company based in Malaysia that provides wireless telecommunications services across the nation. The offers provided by Digi Telecommunication Sdn. Bhd. are mobile and fixed telephony products and services which includes the package of prepaid, postpaid, and international services. The data services is widely serves to individual and corporate customers. The company was formerly known as Mutiara Telecommunications Sdn Bhd before changing the name to Digi Telecommunications Sdn Bhd in January 1999. Digi Telecommunications Sdn Bhd was founded in 1995 and is based in Shah Alam, Malaysia. Digi Telecommunications Sdn Bhd operates as a subsidiary of DiGi.Com Berhad.

Digi Telecommunications Sdn Bhd is telephone and internet connection provider enabling 12.3 million Malaysians to connect with everyone in the world. With the aim to become Malaysians’ favourite life partner, Digi Telecommunications Sdn Bhd focusing on digital connection and lifestyles thanks to 4G+ network. This is because Digi Telecommunications Sdn Bhd believes connection is the important part of human life to build a better world and a better future. As part of the Telenor Group and leader of the rapid pace business growth, Digi has been listed in Bursa Malaysia .

Case Analysis To remain sustain in the fierce competition, Digi Telecommunications Sdn Bhd took an approach by introducing BI in their business work. The BI modelling has been implemented in every department in order to be more standardized the whole departments. A structural equation modelling (SEM) consists of Quality BI Information, Quality BI Users, Quality BI System, BI Governance, Business Strategy, Organization Culture and Use of BI Tool are important criteria in order to guarantee of Successful BI Deployment. The interrelated between all these factors can be seen in Figure 1.

476 International Journal of Academic Research in Business and Social Sciences 2017, Vol. 7, No. 12 ISSN: 2222-6990

Figure 1. BI for sustainable competitive advantage model.

Since Digi Telecommunications Sdn Bhd are keen to implement the foundation of customer-centric organization, they are implemented with CRM system as one of the BI tools. CRM system used in Digi Telecommunications Sdn Bhd presented a full integration in fulfilment order and the billing system that will reduced the manual data entry; reducing the workload and more time-saving. This would help the sales department more focusing on sales and marketing activities and CRM also allows sales agent to foresee the sales progress. For management, this system allows the top managements to create charts and making reports in accounts, sales and marketing, and business line performance. CRM applications is the tool that use Online Analytical Processing (OLAP) and data mining to perform the analytical processes of the data. This section will be focusing on how CRM data mining the vast amount of data in order to produce high quality information for decision making with a reason to stay competitive advantage. The strategy of data collecting and mining using CRM as presented in Figure 2.

477 International Journal of Academic Research in Business and Social Sciences 2017, Vol. 7, No. 12 ISSN: 2222-6990

Figure 2. CRM strategy business and data mining processes.

Raw information ought to be gathered and aggregated to the customer level. Various summary factors can be utilized. The recommendation of data collected are based on the normal call length, the rate of no-answer calls, the rate of calls to/from an alternate region code, the rate of weekday calls (Monday – Friday), the rate of daytime calls (9:00 A.M. – 5:00 P.M.), the average number of calls every day, the average number of calls originated every day. Some different components, as minutes of calls in standard time period, minutes of calls in rebate time period, minutes of calls in evening outline, minutes of local call, minutes of international call, or minutes of the aggregate call can be utilized too. These factors are gotten from call detail information gathered over some day and age (e.g. one, three, or six months).

All components above can be utilized for client profiling, which is a standout amongst the most important data mining applications in Digi Telecommunication Sdn Bhd. Aside than call detail records, CRM store numerous other information in their databases. For instance, it gather data about their clients (name, address, age and sex data). Client information can be utilized as a part of conjunction with call detail information in order to get better data mining result, as shown on Figure 3.

478 International Journal of Academic Research in Business and Social Sciences 2017, Vol. 7, No. 12 ISSN: 2222-6990

Figure 3. Combining call detail and customer data for better data mining results.

CRM will acquires the all the related data of all the organization and how it interconnected with customers’ data. Then, CRM is working into three different areas which are: • Operational Group - This stage will focusing with the automation of business processes that involves first person contact point of Digi Staff. This application plays major role in sale force automation, customer service and marketing.

• Analytical Group - This stage will focusing on customer data analysis, modelling and evaluation. Play major roles in fraud detection.

• Collaborative Group – This stage will focusing on collaborative services and infrastructure that enables the interaction between companies mainly in Network Management. . Table 1. Data Mining using CRM in Digi Telecommunication Sdn Bhd

BI and Data Mining Scope Area Application Areas

479 International Journal of Academic Research in Business and Social Sciences 2017, Vol. 7, No. 12 ISSN: 2222-6990

Marketing, Sales and • Generating client profiles from call detail records and Customer Service digging these profiles for showcasing purposes • Measuring client esteem and holding productive clients • Maximizing the benefit gotten from every client • Discovering affiliation and successive examples to advance Telecommunication administrations • Acquiring new clients • Churn Analysis :- I. Churn forecast: anticipating whether a specific client will agitate and when it will happen II. Churn administration: understanding why specific clients beat and applying endeavours to hold them

Fraud Detection • Identification of potentially fraudulent users and their atypical usage patterns (subscription fraud) • Detecting attempts to gain fraudulent entry to customer accounts (superimposed fraud) • Discovering unusual patterns that may need special attention such as busy-hour, frustrated call attempts, switch and route congestion patterns, etc.

Network • Network blame ID Management • Alarm connection (for relating different alerts to a solitary blame) • Network blame forecast • Identifying and looking at information movement • System work stack administration • Resource use administration • User aggregate conduct

In order to extract the data mining from customers, CRM concerning on two factors which are customer segmentation and churn prediction. These two factors are important to build relevance patterns to CRM for better decision making.

Customer Segmentation Customer Segmentation is gathering comparative clients together, in light of numerous diverse criteria. Along these lines it is conceivable to focus on every last gathering relying upon their qualities. Client division helps organizations create suitable advertising efforts and evaluating systems. One of the famous method using in this process is clustering. By clustering, the data miners or analyst can sort the large amount of data into groups with similar characteristics. The advantages of using clustering techniques is because it covers the complete set of data, findings the missing or dirty data, forming the patterns as shown in Figure 4.

480 International Journal of Academic Research in Business and Social Sciences 2017, Vol. 7, No. 12 ISSN: 2222-6990

Figure 4. The data available for customer segmentation

481 International Journal of Academic Research in Business and Social Sciences 2017, Vol. 7, No. 12 ISSN: 2222-6990

Churn Prediction

Churn prediction is more focus on the future prediction which impact on customer loyalty. By this method, CRM can produce the patterns on how loyal one customer using DiGi services. It is important because the cost of keeping the loyal customers is ten times lower than recruiting the new customers. With the help of CRM, the management can predict the list of possible customers who have high probability leaving the company or port out to other telecommunication companies (competitors). This churn prediction can be break down into two which are voluntary churn and involuntary churn. In voluntary churn, the customers are the first who engages the action. Meanwhile, in involuntary churn, the company took the first action mostly related to service’s cut off, billing and payment process as can be seen in Figure 5.

Figure 5. The data available for churn prediction.

Abilities for data collection have been expanding quickly in all department in Digi Telecommunication Sdn Bhd. The volume of data is relied upon to keep on growing in the future and the organization must be able to handle all these processes very well. That is the reason Digi Telecommunication Sdn Bhd needs to use CRM that can change these immense measures of data into helpful information and knowledge with one ultimate goal; to remain sustain in the competition.

482 International Journal of Academic Research in Business and Social Sciences 2017, Vol. 7, No. 12 ISSN: 2222-6990

Discussion and Recommendations With the use CRM in Digi Telecommunication Sdn Bhd, not only the use of BI help the organization to stay sustain, but also affected the whole operational in the organization in the good ways. One thing that we can see from the changes of environment in Digi Telecommunication Sdn Bhd is through the improvement of intellectual capital. The four capital that affected are Customer capital, Relationship capital, Human capital and Innovation capital. Customer capital – The use of BI tools (CRM) has improved the customer relationship to the company. Once the service quality improved, more new customers joining Digi and more loyal customers has been made. Relationship capital –Through the service network or Digi application on smartphones, the relationship gap between customers and Digi agents also become close. A quick response and feedback can be given to the customers in short time. Human capital- With the use of CRM, it help to bolster the worker’s knowledge, encourage the staff to learn new skills and things and becoming the knowledge- worker. Thus, it will nurture the knowledge sharing culture not only among the workers but to the management also. Innovation capital- CRM provides the knowledge analysis based on behaviour, problems and resources about the clients, services and experiences. This will help Digi Telecommunication Sdn Bhd to keep growing and compete with other competitors.

However, Digi Telecommunication Sdn Bhd also faces a few problems regarding of BI and Data Mining in daily business line. One of the biggest problems is data quality. Some of the processed data did not produced high quality of information for the decision making even though undergone BI and data mining process. Getting of the cross-functional or comprehensive view of information also extremely hard for the company. Another important problem is regarding the needed of more complex pre-processing data, especially data aggregation of semantic level due to data availability in the form of transactions. Besides, scalability is the one of concern that the company need to focus, due to vast amount of data processed day by day and large databases needed to store all of these information. Real-time operation also brings the great importance to the company as far as fraud detection and network connection; since the operation is continuous 24/7 daily. In addition, prediction and strategizing for “unique” events also a challenge to CRM due to the constraints of Data mining algorithms and calculations; resulting to poor decision making and need to rely on to the management experiences in handling similar cases.

Conclusion Business Intelligence (BI) is a business management tool, which comprises of application and technologies that are utilized to accumulate and examine data about the business. Business Intelligence frameworks are used by telecommunication company to break down the components (or information from inside and outside the organization) influencing the nature of business, in order to help them in settling on a decision making process. Different strategy and technologies of Business Intelligence include query reporting and investigation instruments, data mining techniques and data warehousing device. Business Intelligence tool enable the telecommunication company to make the decision at all levels; for example key, strategic and operational, with the help of analytics and powerful data mining tools. In addition, BI will help reducing time for reporting in all level of organization. Telecom organizations work in a profoundly competitive environment.

483 International Journal of Academic Research in Business and Social Sciences 2017, Vol. 7, No. 12 ISSN: 2222-6990

So, why it is important to the telecommunication industry to use data mining? Since the telecommunication industry is undergoing rapid growth and facing the competition challenge every day, they need to handle and process vast amount of data to produce high quality of information for decision making and remain sustain. With a specific end goal to increase competitive advantage they need to: • Understand clients' conduct and behaviour • Interact with clients and convey them progressed and quality services according by customers’ needs.

Data mining models can help them accomplish these objectives by empowering customer segmentation and churn prediction. Data mining can be an extremely successful methods for keeping the customer and for the sustainability of the organization. In today's focused business scene the client is a king, and the sooner one organization understands and deliver the customer’s needs, the better.

References Berry, M.J.A. and Linoff, G.S. (2000), Mastering Data Mining, Wiley, New York, NY. Brachman, R.J., Khabaza, T., Kloesgen, W., Piatetsky-Shapiro, G. and Simoudis, E. (1996),“Mining business databases”, Communications of the ACM, Vol. 39 No. 11, pp. 42-8. Buckman, R.H. (2004), Building a Knowledge-Driven Organizations, McGraw Hill, New York, NY. Chen, S.Y. and Liu, X. (2005), “Data mining from 1994 to 2004: an application- oriented review”, International Journal of Business Intelligence and Data Mining, Vol. 1 No. 1, pp. 4-11. Cody, W.F., Kreulen, J.T., Krishna, V. and Spangler, W.S. (2002), “The integration of business intelligence and knowledge management”, IBM Systems Journal, Vol. 41 No. 4, pp. 697-713. Cook, C. and Cook, M. (2000), The Convergence of Knowledge Management and Business Intelligence, Auerbach Publications, New York, NY. Davenport, T.H. and Seely, C.P. (2006), “KM meets business intelligence: merging knowledge and information at Intel”, Knowledge Management Review, January/February, pp. 10-15. Fayyad, U., Piatetsky-Shapiro, G. and Smyth, P. (1996), “The KDD process for extracting useful knowledge from volumes of data”, Communications of the ACM, Vol. 39 No. 11, pp. 7-34. Feng, D. and Chen, E.T. (2007), “Firm performance effects in relations to the implementation and use of knowledge management systems”, International Journal of Innovation and Learning, Vol. 4 No. 2, pp. 172-85. Foley, K. (2001), “Knowledge management key to collaboration”, InformationWeek, Vol. 857,October 1, p. 78. Glass, R.I. (2007), “What’s with this blog thing?”, IEEE Software, Vol. 24 No. 5, pp. 103-4. GoogleBlogger (2008), available at: www.blogger.com (accessed January 15, 2008). Hall, M. (2004), “Doubtful BI”, Computerworld, Vol. 38 No. 25, p. 45. Hand, D.J. (1998), “Data mining: statistics and more?”, The American Statistician, Vol. 52 No. 2,pp. 112-8.

484 International Journal of Academic Research in Business and Social Sciences 2017, Vol. 7, No. 12 ISSN: 2222-6990

Heinrichs, J.H. and Lim, J. (2003), “Integrating web-based data mining tools with business models for knowledge management”, Decision Support Systems, Vol. 35 No. 1, pp. 103- 12. Herschel, R.T. and Jones, N.E. (2005), “Knowledge management and business intelligence: the importance of integration”, Journal of Knowledge Management, Vol. 9 No. 4, pp. 45- 55. Kaplan, J. (2007), “Data mining as a service: the prediction is not in the box”, DM Review Magazine, July 1. King, J. (2005), “Better decisions”, Computerworld, Vol. 39 No. 38, pp. 48-9. Lavrac, N., Motoda, H., Fawcett, T., Holte, R., Langley, P. and Adriaans, P. (2004), “Introduction:lessons learned from data mining applications and collaborative problem solving”, Machine Learning, Vol. 57, pp. 13-34. Lee, M.C. and Change, T. (2007), “Linking knowledge management and innovation management in e-business”, International Journal of Innovation and Learning, Vol. 4 No. 2, pp. 145-59. Liao, K., Lu, J. and Yi, Y. (2007), “Research on humanised web-based learning model”, International Journal of Innovation and Learning, Vol. 4 No. 2, pp. 186- 96. Loshin, D. (2003), Business Intelligence: The Savvy Manager’s Guide, Morgan Kaufmann, San Francisco, CA. Lu, H. and Hsiao, K. (2007), “Understanding intention to continuously share information on weblogs”, Internet Research, Vol. 17 No. 4, pp. 345-54. MacDougall, R. (2005), “Identity electronic ethos, and blogs: a technologic analysis of symbolic exchange on the new news medium”, The American Behavioral Scientist, Vol. 49 No. 4, pp. 575-99. Malhotra, Y. (2004), “Why knowledge management systems fail: enablers and constraints of knowledge management in human enterprise”, in Koenig, E. and Srikantaiah, T.K. (Eds),Knowledge Management: Lessons Learned, ASIST Monograph Series,

485 www.hrmars.com

Academia.edu no longer supports Internet Explorer.

To browse Academia.edu and the wider internet faster and more securely, please take a few seconds to  upgrade your browser .

Enter the email address you signed up with and we'll email you a reset link.

• We're Hiring!
• Help Center

Data Mining for Technical Operation of Telecommunications Companies: a Case Study

Proceedings of International Conference SCI/ISAS

This paper is an overview of a Data Mining project carried out by the Warsaw University of Technology in the Network Planning and Maintenance Department of a Polish cellular telecom provider. This project has provided an excellent opportunity to test various Data Mining methods on real, non-classic (i.e. mostly not related to purely marketing problems) data from the technology area. In this paper the Data Mining experiment results are presented together with a short description of the applied methods and algorithms. Some remarks on managerial problems that have emerged during the Data Mining techniques implementation in a large corporation have also been included.

Related Papers

Mieczysław Muraszkiewicz , Wiktor B Daszczuk

Data Mining for Technical Operation of Telecommunications Companies: a Case Study Wiktor Daszczuk*, Piotr Gawrysiak*, Tomasz Gerszberg+, Marzena Kryszkiewicz*-HU]\ 0LH FLFNL*, 0LHF]\ VáDZ 0XUDV] NLHZLF] 0LFKDá 2NRQLHZVNL+ HQU\ N 5\ EL VNL***, Tomasz Traczyk♦, Zbigniew Walczak**{wbd, gawrysia, mkr, jms, mrm, okoniews, hrb, walczakz}@ ii. pw. edu. pl Institute of Computer Science, Warsaw University of Technology♦ T. Traczyk@ ia. pw. edu. pl Institute of Control and Computation Engineering, Warsaw ...

IJSRD - International Journal for Scientific Research and Development

Telecommunication companies today are operating in highly competitive and challenging environment. Vast volume of data is generated from various operational systems and these are used for solving many business problems that required urgent handling. These data include call detail data, customer data and network data. Data Mining methods and business intelligence technology are widely used for handling the business problems in this industry. The goal of this paper is to provide a broad review of data mining concepts.

Tejaswini Takale

Zahid A Ansari

Proceedings of the First European Symposium on Principles of Data Mining and Knowledge Discovery

Blaise Egan

Chaturanga Kumarasiri

Adrian Costea

Abstract: Nowadays, the Internet comprises of huge amount of electronic information concerning different companies ’ financial performance. This amount greatly exceeds our capacity to analyze it, the problem being that we often lack tools to quickly and accurately process these data. DM techniques are interesting mechanisms that can be applied to rapidly changing industries, in order to get an overview of the situation. One such market is the international telecommunications industry. In this paper we construct a framework using DM techniques that enables us to make class predictions about telecommunication companies’ financial performance. Our methodology allows us to analyze the movements of the largest telecommunications companies, to see how companies perform financially compared to their competitors, what they are good at, who are the major competitors in this industry, etc. The dataset contains 88 companies from five different regions: Asia, Canada, Continental Europe, Norther...

IJSART JOURNAL

Data mining is the computational process of discovering patterns in large data sets. The overall goal of the data mining process is to extract information from a data set and transform it into an understandable structure for further use. The paper discusses few of the data mining techniques, algorithms and some of the organizations which have adapted data mining technology to improve their businesses and found excellent results and focuses on presenting the applications of data mining in the business environment.

JOURNAL OF XI'AN UNIVERSITY OF ARCHITECTURE & TECHNOLOGY

Dr Adel AL-Alawi

prakash durai

RELATED PAPERS

New Biotechnology

Ernesto Doncel-pérez

PLoS biology

Szabolcs Horvát

RIFKA NIDA NOVALIA 2019

Politics and Governance

Reinhard Heinisch

Silvia Regina Vergilio

Archaeology of the Eurasian Steppes (Arkheologiya Evraziyskikh stepey)

Hand and Microsurgery

Ahmet Karaarslan

Revista Contracampo

Suely Fragoso

Revista de Sociologia e Política

DENISE RATMANN ARRUDA COLIN

Environmental Science and Pollution Research

Deepak Panchal

Susan Hallam

Scientific reports

Anatoly Fedorov

Indian Journal of Endocrine Surgery and Research

Anish Cherian

Rüştü GÜNTÜRKÜN

Revista de la Asociación Argentina de Ortopedia y Traumatología

Lisandro Carbo

Journal of Computing in Higher Education

Sofoklis Sotiriou

Jurnal Ilmu Keluarga dan Konsumen

ANGGI RAHMA SARI

Revista U.D.C.A Actualidad & Divulgación Científica

Juan Velásquez

Frédéric Régent

Rafael Edgardo Carlos Reyes

Manipulación del hombre

Atzy Pantoja

International Journal of Scientific and Research Publications (IJSRP)

Revalda Salakory

Public Management Review

irene georgescu

Panacea Journal of Medical Sciences

Innovative Publication

Nikola Stosic

See More Documents Like This

RELATED TOPICS

•   We're Hiring!
•   Help Center
• Find new research papers in:
• Health Sciences
• Earth Sciences
• Cognitive Science
• Mathematics
• Computer Science
• Academia ©2024

• Skip to main content
• Keyboard shortcuts for audio player

Millions of customers' data found on dark web in latest AT&T data breach

Chloe Veltman

An AT&T store in New York. The telecommunications company said Saturday that a data breach has compromised the information tied to 7.6 million current customers. Richard Drew/AP hide caption

An AT&T store in New York. The telecommunications company said Saturday that a data breach has compromised the information tied to 7.6 million current customers.

AT&T announced on Saturday it is investigating a data breach involving the personal information of more than 70 million current and former customers leaked on the dark web.

According to information about the breach on the company's website, 7.6 million current account holders and 65.4 million former account holders have been impacted. An AT&T press release said the breach occurred about two weeks ago, and that the incident has not yet had a "material impact" on its operations.

AT&T said the information included in the compromised data set varies from person to person. It could include social security numbers, full names, email and mailing addresses, phone numbers, and dates of birth, as well as AT&T account numbers and passcodes.

The company has so far not identified the source of the leak, at least publicly.

"Based on our preliminary analysis, the data set appears to be from 2019 or earlier," the company said. "Currently, AT&T does not have evidence of unauthorized access to its systems resulting in theft of the data set."

AT&T says cell service is back after a widespread outage and some disrupted 911 calls

The company said it is "reaching out to all 7.6 million impacted customers and have reset their passcodes," via email or letter, and that it plans to communicate with both current and former account holders with compromised sensitive personal information. It said it plans to offer "complimentary identity theft and credit monitoring services" to those affected by the breach.

External cybersecurity experts have been brought in to help investigate, it added.

NPR reached out to a few AT&T stores. The sales representatives in all cases said they were as yet unaware of the breach.

On its website, the telecommunications company encouraged customers to closely monitor their account activity and credit reports.

"Consumers impacted should prioritize changing passwords, monitor other accounts and consider freezing their credit with the three credit bureaus since social security numbers were exposed," Carmen Balber, executive director of the consumer advocacy group Consumer Watchdog, told NPR.

An industry rife with data leaks

AT&T has experienced multiple data breaches over the years.

In March 2023, for instance, the company notified 9 million wireless customers that their customer information had been accessed in a breach of a third-party marketing vendor.

In August 2021 — in an incident AT&T said is not connected to the latest breach — a hacking group claimed it was selling data relating to more than 70 million AT&T customers. At the time, AT&T disputed the source of the data. It was re-leaked online earlier this month. According to a Mar. 22 TechCrunch article , a new analysis of the leaked dataset points to the AT&T customer data being authentic. "Some AT&T customers have confirmed their leaked customer data is accurate," TechCrunch reported. "But AT&T still hasn't said how its customers' data spilled online."

AT&T is by no means the only U.S. telecommunications provider with a history of compromised customer data. The issue is rife across the industry. A 2023 data breach affected 37 million T-Mobile customers. Just last month, a data leak at Verizon impacted more than 63,000 people, the majority of them Verizon employees.

A 2023 report from cyber intelligence firm Cyble said that U.S. telecommunications companies are a lucrative target for hackers. The study attributed the majority of recent data breaches to third-party vendors. "These third-party breaches can lead to a larger scale supply-chain attacks and a greater number of impacted users and entities globally," the report said.

Government rules adapt

Meanwhile, last December, the Federal Communications Commission (FCC) updated its 16-year-old data breach notification rules to ensure that telecommunications providers adequately safeguard sensitive customer information. According to a press release , the rules aim to "hold phone companies accountable for protecting sensitive customer information, while enabling customers to protect themselves in the event that their data is compromised."

"What makes no sense is leaving our policies stuck in the analog era," said FCC Chairwoman Jessica Rosenworcel in a statement regarding the changes. "Our phones now know so much about where we go and who we are, we need rules on the books that make sure carriers keep our information safe and cybersecure."

• data breach