Mantian Hu

Evaluating VoLTE Voice Quality in LTE Networks

Voice communication is largely used nowadays by LTE phone users, despite introduction of many Apps on the market. Therefore, mobile voice call quality assessment is still an important metric to evaluate for mobile carriers. Research in assessing speech and voice quality mainly focuses on audio clips analysis. POLQA (standing for Perceptual Objective Listening Quality Assessment) is the standard for voice quality evaluation, taking audio clips as the input and giving an objective quality evaluation.

Profiling Wireless Resource Usage for Mobile Apps

This chapter is devoted to the other side of mobile phone usage, namely the mobile apps. With the spread of LTE technology, network traffic induced by apps brings huge overhead to the mobile network. Profiling wireless resource usage is fundamental for getting better knowledge and identification of the network traffic. It is important to anticipate potential overloading of the bandwidth consumption. Also, it allows improving resource allocation for better quality of services.

Outlier Identification in Telecom Data

This chapter introduces technology to detect anomalies caused by technical equipment problems or fraudulent intrusion in telecommunication networks. The anomaly detection technology extracts information from network raw data and utilizes machine learning algorithms to alert network managers when an anomaly occurs.

Analytics Assisted Self-Optimization in LTE Networks

This chapter concentrates on self-optimization in wireless communication network and primarily introduces SON (Self-Organizing Networks) technology. Self-Organizing network (SON) is an automation technology which is designed to make the planning, deployment, operation, optimization and healing of mobile radio access networks simpler and faster. As the complexity of networks increases and an insatiable demand for mobile broadband continues, the need for SON has never been greater. It is considered as a major necessity in LTE and future 5G networks and operations due to the possible savings in capital expenditure (CAPEX) and operational expenditure (OPEX) by introducing SON in all phases of the network engineering life cycle.

Trending Device Readiness and Device Return Rate

The usage of mobile devices has significantly grown in recent years, and they have become an integral part of our daily lives. They are being designed and manufactured at a rapid rate to satisfy market demand. Companies manufacturing mobile devices and wireless network providers marketing mobile devices may periodically review device return rates and causes of returns after the devices are launched to market. A clear and correct review of device return rate would help the manufacturers or the wireless network providers to determine success of a device model or make alterations to the subsequent design. Like the device return rates, the wireless network operator may also monitor a device’s manufacturing progress to determine whether the device would be available to users based on a particular schedule. Organizations need to determine whether or not a device is ready to be launched into a consumer market.

Methodologies of Analytics for Telecom

The last few years have witnessed a huge increase in the network flow of data, accompanied by a growing amount of data collected by mobile operators. Beyond storage and management of indicators about this flow, a main challenge has been to select and use this mass of material to get a better knowledge of the network. Indeed, since the resulting flow has become impossible to manually process and analyze, simple summarizing statistics of the network traffic have been insufficient to represent the full information contained in those data. This issue has led to the need of new strategies to manage and understand data.

Introduction – Telecommunications Data and Marketing

Starting with this Chapter 9, the rest of this book is devoted to applications and studies specific to telecom marketing. Telecommunication data are of paramount importance; when combined with statistical and econometric models, and machine learning tools, it gives specific insights into consumer behavior. And with better knowledge of consumer behavior, companies (including mobile carriers) can carry out more effective marketing campaigns to better target consumers and enhance its sales performance. In this section of telecom marketing, we focus on four main dimensions: customer identification, customer attraction, customer retention, and customer development. The ideal result is to determine how to predict customer churn rate, to recommend best rate plans, and to develop new services to subscribers. The churn rate problem specifically accommodates customer attraction and retention.

Trending LTE Network Performance

LTE network performance is commonly evaluated from Key Principal Indicators (KPIs), which are relevant numeric indicators summarizing the global performance of the network. A hot topic is to evaluate and forecast those network performance indicators from the available traffic flow and history. This evaluation of LTE network performance is crucial for mobile carriers to leverage appropriate strategies of capacity requirement and management.

Network Based Targeting

In this chapter we demonstrate that when an individual’s network information is available, we can use the characteristics of network structure to improve the predictive validity when predicting consumer behavior (even in out of sample predictions). However, network structure measures are determined by the network itself, and network is the result of individual’s social interactions which is determined by individual characteristics. So we have to develop a structure model of consumer behavior within a network to address the related endogeneity issues.

Social Influence and Dynamic Network Structure

In the previous chapter we discussed how social influence can affect product adoption. In this chapter, we want to further investigate the interplay between network structures and effect of social influence to facilitate diffusion. The role social influence plays in diffusion of new products is often studied for its multiplier effects, which can be helpful in facilitating the diffusion process [1]. These are especially of interest to companies, who can take advantage of social influence in developing marketing strategies.