No full-text available
To read the full-text of this research,
you can request a copy directly from the author.
Customer segmentation for a mobile telecommunications company based on service usage behavior
Abstract
Competition between the mobile operators is becoming more based on subscriber's behavior. In order to improve mobile operator's competitiveness and customer value, several data mining technologies can be used. One of the most important data mining technologies is customer clustering and segmentation. This targeting practice has been proven manageable and effective for mobile telecommunications industry. Most telecommunications carriers cluster their mobile customers by billing system data. This paper discusses how to cluster mobile customers based on their call detail records and analyze their consumer behaviors. Finally, the subscribers categorized in four loyal groups and the strategy to apply has been suggested in a specific life cycle.
... The base needs to be grouped efficiently using clustering models. Each segment needs to have its own mean values [3]. This allows the service providers to target customers in particular segments with better offers, thereby resulting in improved customer satisfaction and revenue generation. ...
... After performing several experiments the best predictor was obtained by using spreading factor of 0.72 and SPA was successful in making correct predictions about 50-60% of future churners. In the domain of Customer segmentation for telecom companies, a study was based on service usage behavior [3] which discussed various clustering techniques to understand customer behavior. Customers were clustered using k-Means based on their CDR and categorized in four loyalty groups. ...
Every telecommunication market player is launching innovative business models and offering better services which in turn have increased the cost of retaining customers. Realizing the importance of customer retention, service providers are now putting more efforts in prediction and prevention of customer churn. This work being divided into two phases, with phase one presenting some of the commonly used data-mining techniques for the identification of churners and customer segmentation based on various Key Performance Indicators (KPIs). While phase two phase discusses how social network analysis extracts relationships between different subscribers to improve the results produced by the traditional learning algorithms at individual subscriber level. Satisfactory results have been achieved from Base model which were significantly enhanced by applying the social network analysis technique.
... While mobile customer data has been used for predicting potential churn [8], prospective customers of electronic money application [9], studying cross-selling potential opportunities [10], all using classification supervised model. Segmentation modeling based on customer usage on voice and data usage along with customer spending has been studied in [11], [12]. While all mentioned research was conducted from a network provider point of view, Rahman et al. [13] examined video consumer behavior from the OTT platform perspective. ...
... Development of services that are more adequate to consumer preferences in the telecom area is also a research topic for the scientific community. For example, in [30] a study is presented of a new customer segmentation mechanism for the mobile telecommunication sector, based on service usage behaviors. This work relies on data mining technologies deployed for customer clustering and segmentation based on their detail call records and data consumption behaviors. ...
The high penetration rate that mobile devices enjoy in to day’s society has facilitated the creation of new digital services, with those offered by operators and content providers standing out. However, even this has failed to encourage consumers to express positive opinions on telecommunication services, especially when compared with other sectors. One of the main reasons of the mistrust shown is the low level of quality of customer service provided an area that generates high costs for the operators themselves, due to the high number of people employed at call centers in order to handle the volume of calls received. To face these challenges, operators launched self-care applications in order to provide customers with a tool that would allow them to autonomously manage the services they have subscribed. In this paper, we present an architecture that provides customized information to customers – a solution that is separate from mobile operating systems and communication technologies.
... The usage data of mobile-phones is used in a variety of different areas, such as during the COVID-19 pandemic [1]- [11], customer segmentation [12], identification of personality traits and lifestyle [13], [14], the analysis of large social networks [15]- [17], hotspot detection [18], prediction of movement [19], mode of transport identification [20], credit scoring [21], disaster recovery [22], [23], analysis of sleeping behavior of the population [24], migration [25] and land usage classification [26], [27]. ...
Evaluating relative changes leads to additional insights which would remain hidden when only evaluating absolute changes. We analyze a dataset describing mobility of mobile phones in Austria before, during COVID-19 lock-down measures until recent. By applying compositional data analysis we show that formerly hidden information becomes available: we see that the elderly population groups increase relative mobility and that the younger groups especially on weekends also do not decrease their mobility as much as the others.
... With six segments, the correct classification of 78.5% is obtained. Aheleroff et al. [43] used data set containing Call Detail Record (CDRs) of a mobile operator, located in the Middle East that has about 35 million mobile subscribers to categorize the subscribers into four loyal groups based on the level of customer's loyalty during their life cycle. The usage patterns are obtained from detailed call/event records based on mobile services such as GPRS/MMS-SMS, including main usage information such as (incoming call number, outgoing call number, call time and date, call duration, call type, location…) which selected as the core items to monitor customer's behavior. ...
Telecom Companies logs customer’s actions which generate a huge amount of data that can bring important findings related to customer’s behavior and needs. The main characteristics of such data are the large number of features and the high sparsity that impose challenges to the analytics steps. This paper aims to explore dimensionality reduction on a real telecom dataset and evaluate customers’ clustering in reduced and latent space, compared to original space in order to achieve better quality clustering results. The original dataset contains 220 features that belonging to 100,000 customers. However, dimensionality reduction is an important data preprocessing step in the data mining process specially with the presence of curse of dimensionality. In particular, the aim of data reduction techniques is to filter out irrelevant features and noisy data samples. To reduce the high dimensional data, we projected it down to a subspace using well known Principal Component Analysis (PCA) decomposition and a novel approach based on Autoencoder Neural Network, performing in this way dimensionality reduction of original data. Then K-Means Clustering is applied on both-original and reduced data set. Different internal measures were performed to evaluate clustering for different numbers of dimensions and then we evaluated how the reduction method impacts the clustering task.
The business world is getting competitive and complex day by day. The customer needs and expectations also changing rapidly. Therefore, making effective strategic marketing decisions in a short time is essential to hold a competitive advantage. Especially in the telecommunication sector, there are lots of data to be handled every day. By analyzing all those data and extracting the most critical insights and use those insights for strategic marketing decisions is essential to remain as the market leader. Today, Big Data Analytics is used to analyses massive databases and find patterns and extract valuable information and insights. Therefore, this research investigates on strategic marketing decisions, Big Data Analytics and how Big Data Analytics use in telecommunication sector to make strategic marketing decisions. Moreover, this research examines how Big Data Analytics can be applied to perform customer segmentation based on Psychographic segmentation by analyzing URLs using artificial neural network techniques. This study will provide suitable recommendations for the telecommunication companies to apply big data analytics to improve the revenue, and finally it points out the possible future study areas.
This study aims to identify telecom customer segments by utilizing machine learning and subsequently develop a web-based dashboard. The dashboard visualizes the cluster analysis based on demographics, behavior, and region features. The study applied analytic pipeline that involved five stages i.e. data generation, data pre-processing, data clustering, clusters analysis, and data visualization. Firstly, the customer’s dataset was generated using Faker Python package. Secondly was the pre-processing which includes the dimensionality reduction of the dataset using the PCA technique and finding the optimal number of clusters using the Elbow method. Unsupervised machine learning algorithm K-means was used to cluster the data, and these results were analyzed and labeled with labels and descriptions. Lastly, a dashboard was developed using Microsoft Power BI to visualize the clustering results in meaningful analysis. According to the results, four customer clusters were obtained. An interactive web-based dashboard called INSIGHT was developed to provide analysis of customer segments based on demographic, behavioral, and regional traits; and to devise customized query for deeper analysis. The correctness of the clustering results was evaluated and achieved a satisfactory Silhouette Score of 0.3853. Hence, the telecom could target their customers accurately based on their needs and preferences to increase service satisfaction.
What motivates consumers to become innovative is an important phenomenon in consumer behavior and is gaining special attention through the concept of motivated consumer innovativeness. The present study is an attempt to create a new segmentation typology for telecom services incorporating social, functional, hedonic, and cognitive motives for classifying a target population into more meaningful homogenous groups through cluster (K-means) analysis. Results of a single cross-sectional survey indicate creation of three distinct consumer segments: logical thinkers, experiencers, and value-driven users in mobile telecom services. The study offers useful implications on developing telecom service marketing mix for successful diffusion and adoption of innovation.
This study is based on data used by a telecommunications industry over a period of 6 months, beginning July 1, 2018, until December 31, 2018. The approached model of customer lifetime value (CLV) was concerned on the sample size of 245,355 records made by cell phones of active prepaid subscribers. The aim of this article is to estimate CLV through survival function with adjusted variables enclosed, for example, marketing cost. To do this, a statistical model was used to predict the individual CLV and confirmed a different finding to some previous study, in which this new finding brings an important message that the telecom providers should take care of customer earlier before too late because after the 10th of tenure, the subscribers can churn the telecom operator’s service. The result of CLV is well supported to segment market. It will also benefit the telecom providers to maintain their market competitiveness.
With the slowing growth of the telecommunication market and the intense competition for existing customers, Customer Churn Management has become a crucial task for all mobile network operators. Recommendation models based on customer behaviors are widely used by operators to provide diverse telecom tariff packages for suitable people and thus improve customer satisfaction. To address the low precision rate and data granularity of prior studies, this study combined rotation forest (ROF) and LightGBM and construct a hybrid algorithm (ROF-LGB). Grid search method was used in parameter tuning, and ten-fold cross-validation method was used to prevent overfitting. Using mobile data generated by operators, ROF-LGB method was tested and compared with other five traditional machine learning methods. The results showed that ROF-LGB method achieved better performance with better precision rate and execution efficiency in telecom tariff package recommendation.
Increasing competition has led telecommunications service providers to develop marketing strategies to retain their customers and attract new customers. Big data analytics offers some promising solutions that can aid telecommunications service providers in raising their revenues as well as designing better business strategies. In this work, we illustrate how usage behaviors of mobile phone users can be used to identify customers that generate more revenue. Additionally, telecommunications companies can also find a number of people in a customer’s network and can potentially use this information for their benefits. The companies can identify the users with a large network and encourage them to serve as ambassadors to promote their services within their networks in exchange for certain incentives. For experimentation in this paper, we used the strath/nodobo dataset (v.2011-03-23) [1] comprising of customers’ phone usage records. Unsupervised classification technique (clustering) is employed to find both high and low mobile usage customers based on the frequency of their calls, messages and their average call duration. Furthermore, users with a large number of outgoing calls and who are connected to many other users are also identified.
Acquiring and retaining the most profitable customers is a big concern of a telecommunication operator to perform more targeted marketing therefore business demand and competition between mobile operators is becoming more based on life cycle of customers in the network. In order to improve customer satisfaction and fulfill requirements, several data mining technologies can be used. Many researches have been performed to calculate the customer value without considering the call/event record generated according to service usage while my research suggested analyses to predict value of customer during their life based on CDRs and EDRs that generated in the network. One of the most important data mining technologies in life time value of customers is customer segments. This targeting practice has been proven effectively for mobile telecommunication industry. Most operators evaluate their customers by information like gender that extracted from billing systems. This paper discusses an innovation to link call/even detail record to the customer segmentation and CLV for a telecommunication business. The subscribers categorized in four segments (loyal groups) during the CLV that influenced based on service usage.
Direct marketing has become more efficient in recent years because of the use of data-mining techniques that allow marketers to better segment their customer databases. RFM (recency, frequency, and monetary value) has been available for many years as an analytical technique. In recent years, more sophisticated methods have been developed; however, RFM continues to be used because of its simplicity. This study investigates RFM, CHAID, and logistic regression as analytical methods for direct marketing segmentation, using two different datasets. It is found that CHAID tends to be superior to RFM when the response rate to a mailing is low and the mailing would be to a relatively small portion of the database, however, RFM is an acceptable procedure in other circumstances. The present article addresses the broader issue that RFM may focus too much attention on transaction information and ignore individual difference information (e.g., values, motivations, lifestyles) that may help a firm to better market to their customers.
Shopping centers are an important part of the UK economy and have been the subject of considerable research. Relying on complex interdependencies between shoppers, retailers and owners, shopping centers are ideal for knowledge management study. Nevertheless, although retailers have been in the forefront of data mining, little has been written on Customer Knowledge Management for shopping centers. In this chapter, the authors aim to demonstrate the possibilities and draw attention to the possible implications of improving customer satisfaction. Aspects of customer knowledge management for shopping centers are considered using analogies drawn from an exploratory questionnaire survey. The objectives of a Customer Knowledge Management system could include increasing rental incomes and bringing new life back into shopping centers and towns.
Clustering of symbolic data, using different validity indices, is proposed for determining the optimal number of meaningful clusters. Symbolic objects include linguistic, nominal, boolean, and interval-type of features, along with quantitative attributes. Clustering in this domain involves the use of symbolic dissimilarity between the objects. The novelty of the method lies in transforming the different clustering validity indices, like Normalized Modified Hubert’s statistic, Davies–Bouldin index and Dunn’s index, from the quantitative domain to the symbolic framework. The effectiveness of symbolic clustering is demonstrated on several real life benchmark data sets.
This study presents the patterns of use for additional services that are currently provided to mobile telecommunication subscribers in Korea. Factor analysis, clustering and quantitative association rules are used to find the service adoption patterns of segmented groups. From the analysis, three types of user groups are identified. The first group consists of a new generation of customers who utilize chargeable additional services using the ‘direct button’, for leisure and entertainment. The younger generation use their mobile phones more frequently than the older generation, and tend to display higher usage patterns for a variety of additional services. The second group utilizes practical additional services that are low-priced or free such as ‘data service’ and ‘phone-to-phone service’ via ‘Caller ID request service’. The customers in the final group are people who have no general usage characteristics. This paper utilizes the association rules found in each cluster to provide strategic guidance to enhance mobile service market of the corresponding group.
Taiwan deregulated its wireless telecommunication services in 1997. Fierce competition followed, and churn management becomes a major focus of mobile operators to retain subscribers via satisfying their needs under resource constraints. One of the challenges is churner prediction. Through empirical evaluation, this study compares various data mining techniques that can assign a ‘propensity-to-churn’ score periodically to each subscriber of a mobile operator. The results indicate that both decision tree and neural network techniques can deliver accurate churn prediction models by using customer demographics, billing information, contract/service status, call detail records, and service change log.
The more a marketing paradigm evolves, the more long-term relationship with customers gains its importance. CRM, a recent marketing paradigm, pursues long-term relationship with profitable customers. It can be a starting point of relationship management to understand and measure the true value of customers since marketing management as a whole is to be deployed toward the targeted customers and profitable customers, to foster customers' full profit potential. Corporate success depends on an organization's ability to build and maintain loyal and valued customer relationships. Therefore, it is essential to build refined strategies for customers based on their value.In this paper, we propose a framework for analyzing customer value and segmenting customers based on their value. After segmenting customers based on their value, strategies building according to customer segment will be illustrated through a case study on a wireless telecommunication company.
For the success of CRM, it is important to target the most profitable customers of a company. Many CRM researches have been performed to calculate customer profitability and develop a comprehensive model of it. Most of them, however, had some limitations and accordingly the customer segmentation based on the customer profitability model is still underutilized. This paper aims at providing an easy, efficient and more practical alternative approach based on the customer satisfaction survey for the profitable customers segmentation. We present a multi- agent-based system, called the survey-based profitable customers segmentation system that executes the customer satisfaction survey and conducts the mining of customer satisfaction survey, socio-demographic and accounting database through the integrated uses of business intelligence tools such as DEA (Data Envelopment Analysis), Self-Organizing Map (SOM) neural network and C4.5 for the profitable customers segmentation. A case study on a Motor company's profitable customer segmentation is illustrated. q 2005 Elsevier Ltd. All rights reserved.