Telecom Operators Research Articles

Telecom Churn Prediction based on Deep Learning Approach

The transition of customers from one telecom operator to another has a direct impact on the company's growth and revenue. Traditional classification algorithms fail to predict churn effectively. This research introduces a deep learning model for predicting customers planning to leave to another operator. The model works on a high-dimensional large-scale data set. The performance of the model was measured against other classification algorithms, such as Gaussian NB, Random Forrest, and Decision Tree in predicting churn. The evaluation was performed based on accuracy, precision, recall, F-measure, Area Under Curve (AUC), and Receiver Operating Characteristic (ROC) Curve. The proposed deep learning model performs better than other prediction models and achieves a high accuracy rate of 91%. Furthermore, it was noticed that the deep learning model outperforms a small size Neural Network for the customer churn prediction.

온라인상 저작권 침해에 대한 대응방안으로서 모색적 금지명령(dynamic injunction)의 도입 연구

On basis of Article 136 of Korean Copyright Act prescribing criminal sanction against copyright infringement crimes, online information which violates Korean Copyright Act can fall under one of online illegal information under Article 44-7 (1) 9 of the Act On Promotion Of Information And Communications Network Utilization And Information Protection. Article 44-7 (Prohibition on Circulation of Unlawful Information) of the Act On Promotion Of Information And Communications Network Utilization And Information Protection (hereinafter “Information and Communications Network Act”) states that “(1) No one may circulate any of the following information through an information and communications network: [omitted] 9. Other information with content that attempts to commit, aids, or abets a crime.” Currently, Korea Communications Standards Commission is actively responding to overseas copyright infringement by viewing information resulting from overseas online piracy as illegal information under Article 44-7 (1) 9 of the Information and Communications Network Act, and by requesting a correction measure which blocks access to overseas online sites from domestic key telecommunication operators. Therefore, the Copyright Act applies to copyright infringement on domestic online sites, but the Information and Communications Network Act and the Korea Communications Standards Act apply to copyright infringement on overseas online sites. In this sense, the regulations on online piracy are bifurcated. However, regular access blocking measures are not suitable for effectively preventing online copyright infringement. Due to the technical structure of the Internet, access blocking measures can be easily bypassed, and in order to avoid access blocking measures, the infringing server can be moved abroad and the pirated contents can be re-hosted and transmitted again. Over the past few years, a new type of injunction has emerged as an effective response to online copyright infringement. It is called as “dynamic injunction.” The dynamic injunction is a legal mechanism that allows the Internet service provider to block both the main domain name and the IP address of the pirated website, and mirror websites which quickly and easily appear under other domain names and thus remain unaffected by the original injunction order as well. This dynamic injunction system was implemented in Australia, Singapore, Spain, Sweden, Austria and the United Kingdom. Hereinafter, this Article looks at overseas legislative examples of dynamic injunction, and, then, propose ways to introduce this system to Korea.

Prediction of RF-EMF Exposure by Outdoor Drive Test Measurements

In this paper, we exploit the artificial neural network (ANN) model for a spatial reconstruction of radio-frequency (RF) electromagnetic field (EMF) exposure in an outdoor urban environment. To this end, we have carried out a drive test measurement campaign covering a large part of Paris, along a route of approximately 65 Km. The electric (E) field strength has been recorded over a wide band ranging from 700 to 2700 MHz. From these measurement data, the E-field strength is extracted and computed for each frequency band of each telecommunication operator. First, the correlation between the E-fields at different frequency bands is computed and analyzed. The results show that a strong correlation of E-field levels is observed for bands belonging to the same operator. Then, we build ANN models with input data encompassing information related to distances to N neighboring base stations (BS), receiver location and time variation. We consider two different models. The first one is a fully connected ANN model, where we take into account the N nearest BSs ignoring the corresponding operator. The second one is a hybrid model, where we consider locally connected blocks with the N nearest BSs for each operator, followed by fully connected layers. The results show that the hybrid model achieves better performance than the fully connected one. Among N∈{3,5,7}, we found out that with N=3, the proposed hybrid model allows a good prediction of the exposure level while the maintaining acceptable complexity of the model.

Supply Chain Coordination of Product and Service Bundling Based on Network Externalities

Since the commercialization of 5G, the government has actively encouraged 5G industry chain enterprises to accelerate the progress of 5G. Bundling is a popular means to expand 5G subscribers and improve 5G market coverage. Considering the characteristics of bundling, this study establishes a secondary supply chain composed of a terminal manufacturer and a telecom operator under the condition of network externality strength. In this supply chain, the product quality of the terminal manufacturer is complementary to the service quality of the telecom operator. Using Steinberg’s theory, we derive the optimal value of each decision variable in a centralized mode and a decentralized mode and take profit maximization as the goal. This paper also designs a contract of bidirectional cost sharing and revenue compensation for supply chain coordination. Finally, the influence of network externality strength and a mass-additive factor on the supply chain is discussed using numerical analysis. The results show that higher network externality strength has a significant impact on product pricing, the quality of each entity and the profit of the supply chain. At the same time, the degree of complementarity between the terminal product quality and the telecommunications service quality affects whether consumers choose to buy contract products. A higher degree of complementarity promotes the market inflow into high-end consumers.

Cost-effectiveness of fibre optic technology deployment in rural area

Studies have shown that the majority of the global population are migrating from rural to urban areas. People are leaving rural areas due to poor services such as poor broadband service. Fibre optic technology has been introduced as a solution to poor broadband quality. However, as a result of the peculiar characteristics of South Africa's rural areas, the majority of the telecommunication operators are hesitant to invest in ICT in rural areas because it tends to be much less profitable. Hence, the study of how cost-effective it would be to deploy a fibre optic network in rural areas as compared to the current wireless (LTE) network remains an open issue. This study investigates the cost-effectiveness of deploying a fibre optic network in the rural area of Mdantsane township, by analysing the installation and operation costs of fibre optic networks in comparison to the cost of wireless (LTE) networks. The finding of the study amongst others showed that while fibre optic networks seem to be great, however, they come at a cost. The cost of drilling and trenching associated with the deployment of fibre optic networks was reported as the key reason why the network deployment is costly. Hence, reducing the cost of drilling and trenching would reduce the cost significantly. The study suggests that, to lower fibre optic deployment costs, network operators should collaborate and share costs through a customised pricing model that benefits both the operators and rural internet users.

Space as an enabler for sustainable digital transformation: The new space race and benefits for newcommers

Disruptive events are the ones that have historically transformed our world. COVID-19 has forced governments and companies to seek transformation in particular in the field of digital. Space has been an enabler for a number of sectorial policies e.g. agriculture, defence, maritime. Digital transformation requires connectivity providing “anything”, “anytime”, “anywhere”. Space as an enabler for digital transformation has become a centerpiece for socioeconomic sustainability and growth. Mega constellations provide telecom services globally and will directly compete with the terrestrial telecom operators, in the next years while the telecom operators should concentrate on the investment of 5G infrastructure. The most promising mega constellation is the one planned by Starlink, which will consist of more than 40,000 satellites in Low Earth Orbit (LEO), with service coverage of the whole surface of Earth. It is to be highlighted that there is no European project of this scale. The strong point of the Starlink mega constellation is the complete vertical integration: satellite design, manufacturing, launching, control, operation and telecom service provision by a single group of companies. The economies of scale which would be achieved could lower the retail prices of the telecom service to levels which will not be viable for the terrestrial telecom operators. Thus a strong dependency of European telecommunications with the non-European mega constellation like Starlink is expected. The European Union is to develop the next flagship programme in the field of connectivity, following the announcement of Commissioner Breton on 15 July. The Commissioner stated that “… we already need to look beyond 5G. I am talking about starting to prepare for 6G of course, but not only. The next paradigm shift is about linking connectivity with space to provide high-speed connectivity everywhere in Europe”. This has been confirmed by the 22 March Action Plan placing it as the next European flagship after Galileo and Copernicus. It will build on Govsatcom, European Quantum Communications Infrastructures. Small countries like Greece have been taking a step by step approach in ensuring the digital transformation of the country. These steps have been at the level of policy, governance, programmatic and financial instruments. The much higher data rates available would change the transmission of data to and from locations. An opportunity arises for new architectures where satellites can provide internet connectivity blend with terrestrial wireless or wired networks. The service to the user will be seamless and unaware of switching between the different infrastructures. This paper will provide an overview how Europe and small member states have been preparing its space related activities in combination with non-space activities for the digital transformation of the country.

MODELLING THE EFFECT OF SELECTED FACTORS OF VIA-THE-TOP CONTENT (OTT) SERVICES IN KENYA

Purpose: The goal of this research was to develop a model for the impact of several factors on OTT adoption in Kenya.
 Materials and Methods: This study employed an explanatory research technique. The target population for this study was limited to 23076 subscribers, who were the active subscribers of Viusasa as of December 2018. Simple random sampling was used to sample form the target population. Data collection was done through a structured questionnaire, which was both in soft and hard copy. Statistical package for social sciences (SPSS v25.0) was utilized to analyze the responses received from the questionnaire. The study generated and used averages, frequencies, and percentages to present the analysis.
 Results: The findings revealed that individual factors (β=0.326, p=0.000), technological factors (β=0.268, p=0.000), organizational factors (users) (β=0.166, p=0.000) and environmental factors (users) (β=0.270, p=0.000) have a positive and significant relationship with the adoption of OTTs in Kenya. Pay TV providers and broadcasting stations that are providing or purpose to provide OTT services to focus on the key individual factors that lead to the adoption of OTT services. Based on the multiple regression findings, the null hypotheses were rejected since the P values were less than 0.05 and thus, there is a significant effect individual factors, technological factors, organizational factors and environmental factors on the adoption of OTT services in Kenya is not statistically significant.
 Unique contribution to theory, practice and policy: The study findings indicate that the theory of diffusion is applicable to the study of factors influencing the adoption of OTT. Pay TV providers and broadcasting stations that were providing or purposed to provide OTT services are encouraged to focus on the key individual factors that lead to the adoption of OTT services. The understandings assisted on the providers improving their relationship with the users and have a bigger market even in terms of the customer base. Telecom operators in Kenya are encouraged to develop competitive OTT services to gain a competitive advantage over the present OTTs’ players.

Spatial Distribution of Base Transceiver Stations in Ile Ife, Nigeria

This paper assesses the spatial distribution of base transceiver stations (BTS) in Ile-Ife, Nigeria. The multi stage sampling technique was employed in the study. The first stage involved the identification of BTS, 50 were identified across the study area, and these were used to obtain information about the physical and locational characteristics of the BTS. Twenty three (23) of the BTS with buildings in their immediate environment were purposively selected. In establishing the location and pattern of distribution of the BTS in Ile-Ife, the nearest neighbor analysis was used. The study revealed a high concentration of BTS erection in area with high concentration of people especially where we have higher institutions and n few residential areas of Ile-Ife. The study further revealed that the distribution of BTS in Ile-Ife are in random form with Rn value of 0.21 and negative z-score (-69.46) which indicates that the BTS are clustered rather than being random or dispersed. The study therefore concludes that telecommunication operators or service providers should be encouraged to adopt the method of collocation which enables different service providers to connect to a mast at a particular place in time. This is done in order to reduce clustering of masts in the study area. K eywords: Base transceiver stations, Location, NCC, Spatial distribution, Telecommunication mast DOI: 10.7176/JEES/12-6-05 Publication date: June 30 th 2022

An efficient enhanced k-means clustering algorithm for best offer prediction in telecom

<span>Telecom companies usually offer several rate plans or bundles to satisfy the customers’ different needs. Finding and recommending the best offer that perfectly matches the customer’s needs is crucial in maintaining customer loyalty and the company’s revenue in the long run. This paper presents an effective method of detecting a group of customers who have the potential to upgrade their telecom package. The used data is an actual dataset extracted from call detail records (CDRs) of a telecom operator. The method utilizes an enhanced k-means clustering model based on customer profiling. The results show that the proposed k-means-based clustering algorithm more effectively identifies potential customers willing to upgrade to a higher tier package compared to the traditional k-means algorithm. Our results showed that our proposed clustering model accuracy was over 90%, while the traditional k-means accuracy was under 70%.</span>

Live Free-Viewpoint Video in Immersive Media Production Over 5G Networks

5G is a key tool for the cloud-based wireless production of audio-visual contents. By providing higher throughput and lower latency than previous mobile network technologies, as well as flexible allocation of network resources, it enables that some content production pipelines, which are currently implemented using wired connectivity, are provided on top of a 5G network. This brings down production costs, reduces environmental impact and increases operational efficiency. In particular, live immersive production services, such as free-viewpoint video (FVV), can be provided in a much more efficient way. In this paper, we address the challenge of producing and streaming FVV services in real time through 5G networks. We have adapted a state-of-the-art FVV system to integrate it within a 5G architecture, using three key technological enablers: mmWave radio access network to support the uplink traffic requirements from FVV cameras, multi-access edge computing to run video processing algorithms with minimum latency, and end-to-end slicing to guarantee a sufficient quality of service (QoS) within the production pipeline. We have built a field trial over the production network of a telecommunication operator, including a mmWave pilot deployment, edge cloud processing, and remote content production, involving three different locations across Spain. We have measured the key performance indicators at the relevant parts of our trial deployment, showing that, with existing 5G technology, it is possible to achieve live FVV production, although with some limitations. We have also analyzed such limitations, obtaining some insights on how the next generation of 5G networks can overcome them to achieve higher quality of experience (QoE).

Modelling the Factors Measuring Customer Service Excellence for Mobile Application Technology Usage in Abu Dhabi

In many areas of business, technological innovation is critical. The ability to use technology to transform organisations is now a requirement in all industries. Nonetheless, technological acceptance has a significant impact on overall corporate performance. Mobile applications are becoming more popular all over the world. As a result, the goal of this research is to look into the technology acceptance model in order to improve customer service in mobile applications. A questionnaire survey was used to collect data from mobile users in Abu Dhabi Municipality. The Partial Least Squares-Structural Equation Modelling (PLS-SEM) technique, aided by SmartPLS software, was used to analyse 396 completed questionnaire forms. The study's findings indicate that perceived usefulness, perceived ease of use, and attitude all have a significant impact on the intention to use technology. The role of intention to use as a moderator is also confirmed, as is the moderating effect of user experience. Furthermore, statistical evidence supports the role of user experience as a moderator in the customer satisfactionexperience. The study's findings give marketing managers and academics a much stronger foundation for recommending CSE strategies. As a result, telecom operators must go above and beyond to improve PU, PEOU, and attitude, as well as develop strategies, inorder to achieve a higher level of CSE.

A mobile traffic load prediction based on recurrent neural network: A case of telecommunication in Afghanistan

This paper investigates the prediction of mobile traffic load based on four variants of recurrent neural networks, which are the simple long short-term memory (LSTM), stacked LSTM, gated recurrent unit (GRU) and bidirectional LSTM. In the considered schemes, the mobile traffic load of 15 min ahead of time is estimated based on the previous mobile traffic load data. The performance of the proposed scheme is verified using realistic traffic load data collected from the base station located in Kabul city, Afghanistan, which belongs to the SALAAM telecommunication operator during December 2020 and January 2021. Through performance evaluation, the authors confirm that the traffic load can be predicted with high accuracy using considered schemes and the GRU-based scheme outperforms other schemes in terms of accuracy.

Sustainable Urban Mobility Boost Smart Toolbox Upgrade

SUMBooST2 research develops universally applicable data science methodology which extracts key urban mobility parameters and origin/destination matrices from the anonymized big data set gathered from telecom operator. The methodology (toolbox) provides transport planners with a method for fast, efficient, and reliable provision of data on movements within the certain area. Origin/destination matrices with modal split will provide transport planners with valid input data for the planning of urban transport systems. The algorithms which separate relevant mobility data from the overall dataset are the unique part of the toolbox. The algorithms to identify passenger car trips are developed in 2020 project SUMBooST, and they are being upgraded in 2021 to detect trips made by active mobility modes and public transport. For the methodology to be valid, it must be implemented in representative number of cities. Previous SUMBooST project included implementation and validation in the City of Rijeka, and SUMBooST2 continues with two other cities, City of Zagreb, and City of Dubrovnik. The aim of the paper is to present innovative toolbox for the boost of sustainable urban planning based on big data science.

SigmaTel: Adoption of distributor management system

The SigmaTel case deals with sales and distribution, channel management, and technology adoption issues. SigmaTel, part of a large and diversified corporate conglomerate, is the largest telecom operator in India. It entered a highly competitive market and quickly rose to the top spot on the back of cheap data and call rates and a strong 4G network. The case is set in 2021 when the company implements Distributor Management System (DMS)—a technology solution to streamline distributor operations. The primary decision point that the case protagonist, Sanjay Prakash, Head of Sales at SigmaTel, Delhi, faces is how to proceed in light of unexpected challenges that the initiative is facing. Should he recommend that SigmaTel proceed with the rollout? If yes, then how does he overcome distributor resistance and conflict? Failure to adopt DMS can impact the strategic business goals of SigmaTel.

Internet blackouts in Africa

Internet blackouts in Africa have largely been examined through the prisms of human rights and economic development. This has resulted in highly negative assessments; Internet shutdowns have widely been branded as violations of the rights of African citizens, and the bane of economic development. However, while unarguably extreme, Internet blackouts are not necessarily unjustified or unwarranted. Even influential bodies such as the International Telecommunications Union (ITU) recognise the need to shut down the Internet under certain circumstances. Governments often justify Internet shutdowns by citing principles or values that are valid in principle. These include protecting their sovereignty, combating ‘rascality’ among telecom operators, and maintaining peace and security. Given this, it is important to examine the extent to which Internet shutdowns in Africa have been justified, or whether they have been used to advance authoritarian rule. To this end, this study uses documentary analysis and critical observations to explore the morality of Internet blackouts in sub-Saharan Africa, and specifically whether or not the recent shutdowns in Cameroon and Nigeria have been justified.

Customer Satisfaction and Complaints Management in the Nigerian Telecommunication Industry

This study examined “Customer Satisfaction and Complaints Management in the Telecommunication Industry in Nigeria”. Specifically, it aimed at finding out the extent to which customers are satisfied or dissatisfied with the services provided by mobile telecommunication operators and to find out the level of customer satisfaction with the ways telecommunication firms handle their complaints. To achieve the objectives of the study, five telecommunication firms were chosen. The research instrument (questionnaire) was administered on a total of five hundred (500) randomly selected customers of MTN, GLOBACOM, Airtel, 9mobile, and Multi-links. Data obtained were coded and analyzed using descriptive and inferential statistics such as the frequency tables, One-way Analysis of Variance (ANOVA) and the t-test for the difference between two population means. The sampling technique used in the study was the multistage cluster sampling. The findings from the research revealed that the proportion of customers who are satisfied with the services provided by mobile telecommunication firms is the same as those that are dissatisfied. It was thus recommended that telecommunication service providers should take bold steps to improve on their services in order to enhance customer satisfaction as this is key to achieving growth and profitability.

Designing Multi-Modal Embedding Fusion-Based Recommender

Recommendation systems have lately been popularised globally. However, often they need to be adapted to particular data and the use case. We have developed a machine learning-based recommendation system, which can be easily applied to almost any items and/or actions domain. Contrary to existing recommendation systems, our system supports multiple types of interaction data with various modalities of metadata through a multi-modal fusion of different data representations. We deployed the system into numerous e-commerce stores, e.g., food and beverages, shoes, fashion items, and telecom operators. We present our system and its main algorithms for data representations and multi-modal fusion. We show benchmark results on open datasets that outperform the state-of-the-art prior work. We also demonstrate use cases for different e-commerce sites.

PROCESSES OF THE TELECOM OPERATOR’S INFORMATION ARCHITECTURE TRANSFORMATION

The subject of the article is the architecture of information systems of telecom operators (BSS/OSS), requirements for it and the processes of its transformation. The goal is to transform the existing information environment of the operator into an open digital ecosystem, in accordance with business and technological requirements for the functionality and architecture of information systems of communication operators, which will introduce new business models, services and products, communication channels, and increase competitiveness. The following tasks were solved at the study: analysis of the current state of telecommunications and information systems used by telecom operators; analysis of requirements for business support and operational information systems, collection and analysis of requirements for the architecture of modern information systems in the field of telecommunications, analysis of the transformation process from the existing BSS/OSS architecture of the communication operator into the target architecture of the digital communications provider, elaboration of a recommendations for an intermediate architecture. To solve these problems, methods of system and business analysis were used, in particular, methods of analysis of software requirements, technologies for developing software application architecture. The following results were obtained. The current state of the telecommunications services industry, the features of the existing information systems of telecommunications operators (BSS/OSS) and the requirements for the architecture of such systems was analyzed. Strategies of transition to modern architecture was considered and analyzed. The target architecture of the digital service provider's information ecosystem and the process of transforming the existing BSS/OSS architecture into the target architecture were considered. Intermediate migration architecture was proposed. Conclusions: the transformation to modern information architecture will ensure compliance of BSS/OSS systems with market requirements and new technologies, adapt to their changes, allow operators to increase competitiveness, reduce operating and capital costs, create technological conditions for open digital ecosystem and transform the operator into a digital services provider. It was recommended to use an intermediate architecture based on the open standardized TMF API for such transformation.

Study on the Growth of Indian Telecom Sector: Evidence from Post- Liberalization Period

The Indian government has taken major steps towards privatization and liberalization of the telecom sector since 1991. As a result, this sector has made tremendous progress by adopting advanced technology and allowing the participation of private telecom operators. The present study highlights the current scenario of Indian telecom sector and examines its growth in the last three decades from 1991 to 2020. For the study, secondary data is used from various sources and descriptive statistical tools are used for the analysis- annual growth rates, compound annual growth rates and percentage shares. The study concludes that there has been a continuous increase in the subscriber base, overall teledensity in both rural and urban areas, number of broadband subscribers and internet subscribers. The share of the public sector has come down, while the share of the private sector has increased remarkably. It is recommended that the Indian government should make the regulatory and policy framework more adaptable to the fast-changing needs of the telecom sector.

The Influence of Ambidextrous Leadership Mediated by Organizational Agility and Digital Business Model Innovation on the Performance of Telecommunication Companies in Indonesia During the Covid-19 Pandemic

Since 2019 and still progressing in 2020, the problems of the three telecommunication operators have experienced a decline in company performance, it can be seen that TELKOM has decreased revenue from 135.567 Trillion (2019) to 135.450 Trillion (2020). The Covid-19 pandemic that occurred in Indonesia caused telecommunications operators to decide to delay investment in infrastructure development (New Capex) for 2020 and 2021. The purpose of this study was to determine the effect of Ambidextrous leadership mediated by organizational agility and digital business models on performance. telecommunications companies in Indonesia during the COVID-19 Pandemic. This research will be conducted using quantitative research. The sampling technique was done by convenience sampling. The number of samples is 100 respondents. Based on the discussion above, it is concluded that Ambidextrous Leadership has a positive and significant effect on Digital Business Model Innovation, Ambidextrous Leadership has a positive and significant impact on Organizational Agility, Ambidextrous Leadership has a positive and significant impact on Company Performance, Digital Business Innovation Model has a positive and significant impact on Company Performance, Organizational Agility has no positive and significant effect on Company Performance, Organizational Agility is not proven to moderate Digital Business Model Innovation on Company Performance. The study suggests the utilization of extraordinary plans in identifying external and internal situations during and after the corona virus pandemic (COVID-19).