Combining Local and Social Network Classifiers to Improve Churn Prediction

Backiel, Aimée; Verbinnen, Yannick; Baesens, Bart; Claeskens, Gerda

doi:10.1145/2808797.2808850

Cited by 14 publications

(12 citation statements)

References 40 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It is used to model a 'word-of-mouth' scenario, where influence-in this case from delinquent customersspreads through the network. 'Word-of-mouth' has been shown to be effective in social networks [37,38]. Before the method begins, a set of active nodes V A ⊂ V possesses the energy E 0 (V A ).…”

Section: Spreading Activationmentioning

confidence: 99%

The value of big data for credit scoring: Enhancing financial inclusion using mobile phone data and social network analytics

Óskarsdóttir

Bravo

Sarraute³

et al. 2019

Applied Soft Computing

Self Cite

145

View full text Add to dashboard Cite

Credit scoring is without a doubt one of the oldest applications of analytics. In recent years, a multitude of sophisticated classification techniques have been developed to improve the statistical performance of credit scoring models. Instead of focusing on the techniques themselves, this paper leverages alternative data sources to enhance both statistical and economic model performance. The study demonstrates how including call networks, in the context of positive credit information, as a new Big Data source has added value in terms of profit by applying a profit measure and profit-based feature selection. A unique combination of datasets, including call-detail records, credit and debit account information of customers is used to create scorecards for credit card applicants. Call-detail records are used to build call networks and advanced social network analytics techniques are applied to propagate influence from prior defaulters throughout the network to produce influence scores. The results show that combining call-detail records with traditional data in credit scoring models significantly increases their performance when measured in AUC. In terms of profit, the best model is the one built with only calling behavior features. In addition, the calling behavior features are the most predictive in other models, both in terms of statistical and economic performance. The results have an impact in terms of ethical use of call-detail records, regulatory implications, financial inclusion, as well as data sharing and privacy.

show abstract

Section: Spreading Activationmentioning

confidence: 99%

The value of big data for credit scoring: Enhancing financial inclusion using mobile phone data and social network analytics

Óskarsdóttir

Bravo

Sarraute³

et al. 2019

Applied Soft Computing

Self Cite

145

View full text Add to dashboard Cite

show abstract

“…Varun and Ravikumar [10] preprocess data by calculating the Euclidean distance of call duration, the number of calls, SMS messages sent and the buyer's age. A group of authors [11] calculate connection weight by summing up duration of calls between the telecom users. Since mathematical calculations needed to analyze social networks are very demanding, the data for one municipality in Bosnia and Herzegovina was taken, with approximately the same number of domicile network users and sub-scribers who are members of the virtual network.…”

Section: Data Preprocessingmentioning

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

“…The spreading activation method was introduced by Dasgupta et al (2008) and is frequently applied to churn prediction in telco (Backiel et al, 2015). It attempts to simulate the word-of-mouth effect of churn thereby spreading 'churn influence' through the network by the means of a diffusion process.…”

Section: A14 Spreading Activation Relational Classifiermentioning

confidence: 99%

Social network analytics for churn prediction in telco: Model building, evaluation and network architecture

Óskarsdóttir

Bravo

Verbeke

et al. 2017

Expert Systems with Applications

Self Cite

View full text Add to dashboard Cite

Social network analytics methods are being used in the telecommunication industry to predict customer churn with great success. In particular it has been shown that relational learners adapted to this specific problem enhance the performance of predictive models. In the current study we benchmark different strategies for constructing a relational learner by applying them to a total of eight distinct call-detail record datasets, originating from telecommunication organizations across the world. We statistically evaluate the effect of relational classifiers and collective inference methods on the predictive power of relational learners, as well as the performance of models where relational learners are combined with traditional methods of predicting customer churn in the telecommunication industry.Finally we investigate the effect of network construction on model performance; our findings imply that the definition of edges and weights in the network does have an impact on the results of the predictive models. As a result of the study, the best configuration is a non-relational learner enriched with network variables, without collective inference, using binary weights and undirected networks. In addition, we provide guidelines on how to apply social networks analytics for churn prediction in the telecommunication industry in an optimal way, ranging from network architecture to model building and evaluation.

show abstract

Combining Local and Social Network Classifiers to Improve Churn Prediction

Cited by 14 publications

References 40 publications

The value of big data for credit scoring: Enhancing financial inclusion using mobile phone data and social network analytics

The value of big data for credit scoring: Enhancing financial inclusion using mobile phone data and social network analytics

Clique Comparison and Homophily Detection in Telecom Social Networks

Social network analytics for churn prediction in telco: Model building, evaluation and network architecture

Contact Info

Product

Resources

About