Collective Churn Prediction in Social Network

Oentaryo, Richard J.; Lim, Ee-Peng; Lo, David; Zhu, Feida; Prasetyo, Philips Kokoh

doi:10.1109/asonam.2012.44

Cited by 34 publications

(14 citation statements)

References 13 publications

(18 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Researchers have also studied sustainability in other settings; such as social networks [5,13,12] and telecommunication networks [15,7] where the goal is to analyze the cascades of users leaving the network. Different from users leaving Q&A sites, the type of churn in such networks has more of a social context, where one's friends leaving impacts 0 Figure 5: Churn prediction accuracy when features from each category are used in isolation, (left) as k varies and (right) as T varies.…”

Section: Related Workmentioning

confidence: 99%

User churn in focused question answering sites

Pudipeddi

Akoglu

Tong

2014

Proceedings of the 23rd International Conference on World Wide Web

View full text Add to dashboard Cite

Given a user on a Q&A site, how can we tell whether s/he is engaged with the site or is rather likely to leave? What are the most evidential factors that relate to users churning? Question and Answer (Q&A) sites form excellent repositories of collective knowledge. To make these sites selfsustainable and long-lasting, it is crucial to ensure that new users as well as the site veterans who provide most of the answers keep engaged with the site. As such, quantifying the engagement of users and preventing churn in Q&A sites are vital to improve the lifespan of these sites.We study a large data collection from stackoverflow.com to identify significant factors that correlate with newcomer user churn in the early stage and those that relate to veterans leaving in the later stage. We consider the problem under two settings: given (i) the first k posts, or (ii) first T days of activity of a user, we aim to identify evidential features to automatically classify users so as to spot those who are about to leave. We find that in both cases, the time gap between subsequent posts is the most significant indicator of diminishing interest of users, besides other indicative factors like answering speed, reputation of those who answer their questions, and number of answers received by the user.

show abstract

Section: Related Workmentioning

confidence: 99%

User churn in focused question answering sites

Pudipeddi

Akoglu

Tong

2014

Proceedings of the 23rd International Conference on World Wide Web

View full text Add to dashboard Cite

show abstract

“…A proposal that considers different kinds of factors that could influence the churning process in individuals is introduced in [27]. The authors use the idea of Collective Classification (CC) to examine local characteristics and interdependencies between individuals in a group.…”

Section: Social Churning Predictionmentioning

confidence: 99%

A social model based on customers’ profiles for analyzing the churning process in the mobile market of data plans

Postigo-Boix

Melús-Moreno

2018

Physica A: Statistical Mechanics and its Applications

View full text Add to dashboard Cite

Mobile Network Operators (MNOs) present wireless services of the same kind in identical zones, clients select the service taking into account any element they consider relevant. Churning hits on the design of the network and the method to assign prices by MNOs, and of course their earnings. Therefore, MNOs try to reduce churn detecting potential churners before they leave the service. Our approach to churn prediction considers each customer individually. Previous research shows that members of the social circle of a subscriber may influence churn. Thus, many scenarios that describe social relations, and in which churning processes could be expected, set an emerging challenge with practical implications. This paper uses the Agent-Based Modelling (ABM) technique to model customers. The model’s parameters include demographic and psychographic features as well as usage profiles according to their social behavior considering their customers’ profiles. Our model modifies and extends an existing real social network generator algorithm that considers customer’s profiles and homophily considerations to create connections. We show that using our approach, groups of customers with greater tendency to churn due to the influence of their social networks can be identified better.Peer ReviewedPostprint (author's final draft

show abstract

“…Studies such as Dror G et al [18] tried a variety of models in the churn prediction, including Logistic regression, SVM, KNN. Studies such as Oentaryo R J et al [9] used SVM and based on SVM improved ICA model. Studies such as Long X et al [16] used K-means model.…”

Section: Related Workmentioning

confidence: 99%

“…Churn factors analysis: Some scholar the choice of the user's basic features in the social network, such as Richard J. Oentaryo et al [9] chose the user age, gender, nationality, religion, social age, etc.. For structure factors analysis in the social network, Marcel Karnsted et al [10] selected the social nodes of degree, penetration, the central node, and intermediate structural features. Zhu Y et al [14]studied user activity levels in social network, Long X et al [17] researched user relationship in social network.User churn model: there are many domestic and foreign scholars using data mining method to build user churn model, including classification model, the regression model, the clustering model, time series analysis.…”

Section: Related Workmentioning

confidence: 99%

“…Churn problem has got great attention. A large number of industries were study user churn, especially based on the service industry, including the telecommunications [4,5], banking [6], online gaming [7], P2P networks [8], and online social networks [9,10]. Churn problems of online social networks is particularly important, directly affects the economic benefits of social platforms.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

A Churn Prediction Iterative Model in Social Network Based on Relationship Strength

Liu¹,

Liu²,

Xiao³

2017

dtcse

View full text Add to dashboard Cite

Abstract. The existing research of churn prediction in social network mainly consider single individual behavior and adjacent relationship structure, we propose a churn prediction iterative model in social network based on relationship strength. First of all, according to the traditional model, we put forward a hierarchical structure approach to measure the strength of social relationship based on the traditional user relationships and the complexity of social theory. Secondly, from the two angles of the user's activity and user's influence, we apply iterative way to calculate the influence factor of the social environment. And based on conditional probability model, we put forward a churn prediction iterative model in social network (CIM). Experiments show that the model is suitable for the churn prediction in social network with a good effect, and improve the accuracy on churn prediction in social network.

show abstract

Collective Churn Prediction in Social Network

Cited by 34 publications

References 13 publications

User churn in focused question answering sites

User churn in focused question answering sites

A social model based on customers’ profiles for analyzing the churning process in the mobile market of data plans

A Churn Prediction Iterative Model in Social Network Based on Relationship Strength

Contact Info

Product

Resources

About