Mining of leaders in mobile telecom social networks

Ouyang, Ye; Hu, Mantian; Huet, Alexis; Sun, Xingshuai

doi:10.1109/wts.2016.7482054

Cited by 2 publications

(3 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…SNA is a set of analytic methods used to show and measure connectivity and interaction between people, groups, organizations, computers and other connectable entities [15]. Common usage of an SNA in the telecom industry involves the identification of the most influential users in the telecom network [16], the identification of communities and groups [17], fraud detection [18], tariff model recommendation system [19] and predicting telecom churn [8,[20][21][22].…”

Section: Social Network Analysis (Sna)mentioning

confidence: 99%

Churn Prediction Model Improvement Using Automated Machine Learning with Social Network Parameters

Mandić¹,

Kraljević²

2022

RIA

View full text Add to dashboard Cite

Due to strong competition in the telecom market, telecom companies are facing customer churn problems. For telecom, it is very important to predict the churn of a user to be able to prevent it. Marketing campaigns can be used to prevent churn and thus prevent a decrease in revenue. Usually, the churn prediction is based on behavioural user data, which describes user activity and general user data. In our prediction model, we added social network attributes that describe the social influence of other users on the user's decision to make a churn. Besides standard centrality measures, we developed two new social attributes, which measure the social influence of already churned users. To determine if social network attributes aid in churn prediction precision we created and compared the models based only on the behavioural data and the models with the social attributes and behavioural data. In our work, we propose upgrading the standard Automated Machine Learning (AutoML) model with the part of the model related to Social Network Analysis (SNA), and we use the proposed model in our research. We show that the AutoML can be used to successfully predict telecom churn based on the real data from telecom operators from Bosnia and Herzegovina.

show abstract

Section: Social Network Analysis (Sna)mentioning

confidence: 99%

Churn Prediction Model Improvement Using Automated Machine Learning with Social Network Parameters

Mandić¹,

Kraljević²

2022

RIA

View full text Add to dashboard Cite

show abstract

“…One of the ways for extracting knowledge from detailed data is to create and analyze social networks. The usage of SNA in the telecom industry mostly refers to churn [1], fraud detection, a tariff model recommendation system [2], the identification of central nodes in the network [3], and the identification of communities and groups [4]. In this paper, emphasis is placed on community detection in social networks.…”

Section: Introductionmentioning

confidence: 99%

“…Telecoms need to identify key subscribers that have a large number of connections with other subscribers. Key subscribers can influence the opinion and decisions of other subscribers [3]. Keeping a subscriber with a great influence on other subscribers could, on a large scale, decrease the churn rate.…”

Section: Introductionmentioning

confidence: 99%

Clique Comparison and Homophily Detection in Telecom Social Networks

Mandić

Škobić

Martinović

2019

Int. j. electr. comput. eng. syst. (Online)

View full text Add to dashboard Cite

Social Network Analysis (SNA) is based on graph theory and is used for identification of the structure, behavioral patterns and social connectivity of entities. In this paper, SNA is used in the telecom industry in terms of a call detail record referring to phone call data separated into two groups, i.e., domicile network and virtual operator network data. Emphasis was placed on community detection. Comparison was made among communities detected in domicile and virtual operator networks. Results show that in contrast to domicilenetwork, the number of cliques in the virtual operator network is larger. Also, homophily was detected between domicile network and virtual operator network users.

show abstract

Mining of leaders in mobile telecom social networks

Cited by 2 publications

References 11 publications

Churn Prediction Model Improvement Using Automated Machine Learning with Social Network Parameters

Churn Prediction Model Improvement Using Automated Machine Learning with Social Network Parameters

Clique Comparison and Homophily Detection in Telecom Social Networks

Contact Info

Product

Resources

About