Conference Paper

Experience: towards automated customer issue resolution in cellular networks

Authors:
To read the full-text of this research, you can request a copy directly from the authors.

No full-text available

Request Full-text Paper PDF

To read the full-text of this research,
you can request a copy directly from the authors.

... In the last decade, Machine Learning (ML) and Artificial Intelligence (AI) algorithms achieved tremendous performance in several real-life applications (e.g., Banking [1], Marketing [12], Energy [7]). Modern companies are using these cutting-edge solutions to achieve market differentiation and drive value growth through customer experience. ...
... In [11] a novel classification method using machine learning algorithms for customer experience survey analysis is proposed. In addition, in [12] the authors propose a novel approach to to predict customers loyalty, using a combination of customers' satisfaction and network data logs. In [6], a systematic review of the literature in the big data spectrum with respect to the constructs of the customer analytics is provided. ...
Conference Paper
Net promoter score (NPS) is a market research metric that measures customer's satisfaction and its analysis is combined with various parameters/drivers. The paper addresses a core problem in customer experience analytics which is related with the deeper understanding of the drivers of indices in NPS and defines the key drivers that are of utmost importance in describing the customer's experience. To this end, state of the art Explainable Artificial Intelligence (XAI) techniques are applied so as to reveal the role of certain customer experience features and support companies in their decision making process.
... Therefore, how to prevent the IC users from churning by predicting the churn actions in advance also becomes crucial for the market system. In the literature, there have been some studies focused on user usage pattern and behavior modeling in cellular networks [7]- [11], which, however, are targeted on TC users and quite different from our goal that targeted at IC users. On the other hand, user churn prediction has also been investigated [12], [13]. ...
... There have been some user behavior mining studies [7], [9], [10], [19], [20]. Particularly, the authors of [11] performed a qualitative and quantitative user behavior study by adopting a mixed-methods approach, the goal of which is to understand various facts of user behavior in online car-sharing systems. ...
... In the literature, there have been numerous research works focusing on service design based on cellular mobility data, e.g., urban planning and intelligent transportation [40][41][42], location-based services [14,43,44], smart cities [45][46][47][48], emergency response and disaster management [49][50][51], etc. For instance, based on large-scale cellular data, Schläpfer et al. [40] presented an understanding study on the universal patterns observed in human mobility. ...
Article
Full-text available
The scarcity of publicly available cellular association traces hinders user location-based research and various data-driven services, highlighting the importance of data synthesis in this field. In this paper, we investigate the cellular association trace synthesis (CATS) problem, aiming to generate diverse and realistic cellular association traces based on road segment-based trajectories and corresponding departure times. To substantiate our research, we first gather substantial data, including road segment-based trajectories, base station (BS) distribution, and ground truths of cellular association traces. We then perform systematic data analysis to reveal technical challenges such as disparity in geographic spaces, complex and dynamic BS handover, and poor performance of single-dimension approaches. To address these challenges, we propose SynthCAT, a novel scheme that fuses model-based and data-driven approaches. Specifically, SynthCAT includes: i) A model-based coarse-grained cellular association trace generation component, encompassing GPS reference generation, weighted historical average time generation, Bayesian decision, and time mapping modules. This component establishes a unified GPS space to map road and BS spaces, generates initial time information, synthesizes coarse-grained spatial cellular association traces by following explicit BS handover rules, and maps the corresponding arrival time for each trace point; ii) A fine-grained cellular association trace generation component, which combines model-based and data-driven approaches. This employs a two-stage Autoencoder Generative Adversarial Network (AEGAN) to refine cellular association traces based on the coarse-grained ones. Extensive field experiments validate the efficacy of SynthCAT in terms of trace similarity to ground truths and its efficiency in supporting practical downstream applications.
... Very recently, machine learning methods have been employed to estimate customers' experience in specific types of applications. For instance, in [17], the experience gained in a shopping mall is described, while [18,19], examine and automated customer issue resolution method for cellular communication networks. Finally, in [12], a novel classification method for customer experience survey analysis is proposed. ...
... Very recently, machine learning methods have been employed to estimate customers' experience in specific types of applications. For instance, in [17], the experience gained in a shopping mall is described, while [18,19], examine and automated customer issue resolution method for cellular communication networks. Finally, in [12], a novel classification method for customer experience survey analysis is proposed. ...
Article
Full-text available
Customer Experience (CX) is monitored through market research surveys, based on metrics like the Net Promoter Score (NPS) and the customer satisfaction for certain experience attributes (e.g., call center, website, billing, service quality, tariff plan). The objective of companies is to maximize NPS through the improvement of the most important CX attributes. However, statistical analysis suggests that there is a lack of clear and accurate association between NPS and the CX attributes’ scores. In this paper, we address the aforementioned deficiency using a novel classification approach, which was developed based on logistic regression and tested with several state-of-the-art machine learning (ML) algorithms. The proposed method was applied on an extended data set from the telecommunication sector and the results were quite promising, showing a significant improvement in most statistical metrics.
Article
Full-text available
Cellular Internet card (IC) as a new business model emerges, which penetrates rapidly and holds the potential to foster a great business market. However, with the explosive growth of IC users, the user churn problem becomes severe, affecting the IC business significantly, while there is lacking appropriate techniques in the literature to deal with the issue. In this paper, we take the lead to study one large-scale data set from a provincial network operator of China, which contains about 4 million IC users and 22 million traditional card (TC) users. We first justify the IC user churn issue with data, and categorize the user churning reasons. Then, we shed light on understanding user portraits, which is the building block to enable efficient model design. Particularly, we conduct a systematical analytics on usage data by studying the difference of two types of users, examining the impact of user properties, and characterizing the user Internet using behaviors. Finally, by using the IC user portraits and usage patterns, we propose an IC user C hurn P rediction model, named ICCP , which consists of a feature extraction component and a learning-based churn prediction architecture design. For feature extraction, both the static portrait features and temporal sequential features are captured. In the learning architecture, we devise the principal component analysis (PCA) block and the embedding/transformer layers to learn the respective information of two types of features, which are collectively fed into the classification multilayer perceptron layer (MPL) for churn prediction. A reference implementation of ICCP is conducted within the telecom system and extensive experiments corroborate the efficiency of ICCP .
Conference Paper
Full-text available
Effective management of large-scale cellular data networks is critical to meet customer demands and expectations. Customer calls for technical support provide direct indication as to the problems customers encounter. In this paper, we study the customer tickets - free-text recordings and classifications by customer support agents - collected at a large cellular network provider, with two inter-related goals: i) to characterize and understand the major factors which lead to customers to call and seek support; and ii) to utilize such customer tickets to help identify potential network problems. For this purpose, we develop a novel statistical approach to model customer call rates which account for customer-side factors (e.g., user tenure and handset types) and geo-locations. We show that most calls are due to customer-side factors and can be well captured by the model. Furthermore, we also demonstrate that location-specific deviations from the model provide a good indicator of potential network-side issues.
Conference Paper
Full-text available
Churn prediction aims to identify subscribers who are about to transfer their business to a competitor. Since the cost associated with customer acquisition is much greater than the cost of customer retention, churn prediction has emerged as a crucial Business Intelligence (BI) application for modern telecommunication operators. The dominant approach to churn prediction is to model individual customers and derive their likelihood of churn using a predictive model. Recent work has shown that analyzing customers' interactions by assessing the social vicinity of recent churners can improve the accuracy of churn prediction. We propose a novel framework, termed Group-First Churn Prediction, which eliminates the a priori requirement of knowing who recently churned. Specifically, our approach exploits the structure of customer interactions to predict which groups of subscribers are most prone to churn, before even a single member in the group has churned. Our method works by identifying closely-knit groups of subscribers using second order social metrics derived from information theoretic principles. The interactions within each group are then analyzed to identify social leaders. Based on Key Performance Indicators that are derived from these groups, a novel statistical model is used to predict the churn of the groups and their members. Our experimental results, which are based on data from a telecommunication operator with approximately 16 million subscribers, demonstrate the unique advantages of the proposed method. We further provide empirical evidence that our method captures social phenomena in a highly significant manner.
Article
Full-text available
We explore techniques from statistical machine learning to predict churn and, based on these predictions, to determine what incentives should be offered to subscribers to improve retention and maximize profitability to the carrier. The techniques include legit regression, decision trees, neural networks, and boosting. Our experiments are based on a database of nearly 47000 USA domestic subscribers and includes information about their usage, billing, credit, application, and complaint history. Our experiments show that under a wide variety of assumptions concerning the cost of intervention and the retention rate resulting from intervention, using predictive techniques to identify potential churners and offering incentives can yield significant savings to a carrier. We also show the importance of a data representation crafted by domain experts. Finally, we report on a real-world test of the techniques that validate our simulation experiments
Conference Paper
User feedback data, generated when users call customer care agents with problems, is a valuable source of data for understanding network problems from users' perspectives. However, this data is extremely noisy. In this paper, we design a framework, LOTUS, to assess the user impact of network events from the user feedback, through a novel algorithmic composition of co-training and spatial scan statistics. Through experimental analysis on synthetic and real data, we show the accuracy and practical nature of LOTUS.
Conference Paper
In an increasingly mobile connected world, our user experience of mobile applications more and more depends on the performance of cellular radio access networks (RAN). To achieve high quality of experience for the user, it is imperative that operators identify and diagnose performance problems quickly. In this paper, we describe our experience in understanding the challenges in automating the diagnosis of RAN performance problems. Working with a major cellular network operator on a part of their RAN that services more than 2 million users, we demonstrate that fine-grained modeling and analysis could be the key towards this goal. We describe our methodology in analyzing RAN problems, and highlight a few of our findings, some previously unknown. We also discuss lessons from our attempt at building automated diagnosis solutions.
Article
In spite of its wide use, the concept attitude is not defined uniformly by contemporary writers. While the great diversity of the past has diminished, there remain two distinct conceptions of the term. Probability conceptions emphasize the consistency shown by subjects in responding in defined ways toward attitudinal stimuli. Latent process conceptions assume that such response consistencies are manifestations of "underlying" variables, which also mediate or define the form of attitudinal behavior. A series of logical implications is associated with each of these views. The latent process conception appears inconsistent with the findings of recent attitude research.
Conference Paper
Customer care calls serve as a direct channel for a service provider to learn feedbacks from their customers. They reveal details about the nature and impact of major events and problems observed by customers. By analyzing the customer care calls, a service provider can detect important events to speed up problem resolution. However, automating event detection based on customer care calls poses several significant challenges. First, the relationship between customers' calls and network events is blurred because customers respond to an event in different ways. Second, customer care calls can be labeled inconsistently across agents and across call centers, and a given event naturally give rise to calls spanning a number of categories. Third, many important events cannot be detected by looking at calls in one category. How to aggregate calls from different categories for event detection is important but challenging. Lastly, customer care call records have high dimensions (e.g., thousands of categories in our dataset). In this paper, we propose a systematic method for detecting events in a major cellular network using customer care call data. It consists of three main components: (i) using a regression approach that exploits temporal stability and low-rank properties to automatically learn the relationship between customer calls and major events, (ii) reducing the number of unknowns by clustering call categories and using L1 norm minimization to identify important categories, and (iii) employing multiple classifiers to enhance the robustness against noise and different response time. For the detected events, we leverage Twitter social media to summarize them and to locate the impacted regions. We show the effectiveness of our approach using data from a large cellular service provider in the US.
Conference Paper
Recent work has studied user development in the domains of both telecommunication and online community platforms, examining how users develop in terms of the company they keep (socially) and the language they use (lexically). Such works afford key insights into user changes along individual dimensions, yet they do not examine how users develop relative to their prior behaviour along multiple dimensions. In this paper we examine how users develop along various properties (in-degree, out-degree, posted terms) in three online community platforms (Facebook, SAP Community Network, and Server Fault) and using three models of user development: (i) isolated lifecycle periods, (ii) historical contrasts, and (iii) community contrasts. We present an approach to mine the lifecycle trajectories of users as a means to characterise user development along the different properties and development models, and demonstrate the utility of such trajectories in predicting churners. We find consistent effects with past work: users tend to reflect the behaviour of the community in early portions of their lifecycles, before then diverging from the community towards the end. We also find that users form sub-communities with whom they communicate and remain within.
Article
Let x and y be two random variables with continuous cumulative distribution functions f and g. A statistic U depending on the relative ranks of the x's and y's is proposed for testing the hypothesis f=gf = g. Wilcoxon proposed an equivalent test in the Biometrics Bulletin, December, 1945, but gave only a few points of the distribution of his statistic. Under the hypothesis f=gf = g the probability of obtaining a given U in a sample of nxsn x's and mysm y's is the solution of a certain recurrence relation involving n and m. Using this recurrence relation tables have been computed giving the probability of U for samples up to n=m=8n = m = 8. At this point the distribution is almost normal. From the recurrence relation explicit expressions for the mean, variance, and fourth moment are obtained. The 2rth moment is shown to have a certain form which enabled us to prove that the limit distribution is normal if m,nm, n go to infinity in any arbitrary manner. The test is shown to be consistent with respect to the class of alternatives f(x)>g(x)f(x) > g(x) for every x.
Juggling the jigsaw: Towards automated problem inference from network trouble tickets
  • R Potharaju
  • N Jain
  • C Potharaju
  • R Jain
  • Potharaju R.