A recommender system to avoid customer churn: A case study

Wang, Yifan; Chiang, Ding-An; Hsu, Mei‐Hua; Lin, Cheng-Jung; Lin, I-Long

doi:10.1016/j.eswa.2008.10.089

Cited by 31 publications

(10 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In the study of telecommunication company Wang et al, (2009) used a decision tree to explore 60000 transaction records from 4000 customers communications during a three-month period. According to the rules obtained from their model, the customer's final connection to the network and the number of network connections were identified as the variables helping predict customer churning or loyalty behavior.…”

Section: Empirical Research Backgroundmentioning

confidence: 99%

A Stacking-Based Data Mining Solution to Customer Churn Prediction

Shabankareh

Nazarian

et al. 2021

Journal of Relationship Marketing

View full text Add to dashboard Cite

In today's competitive world, organizations are in a constant struggle to retain their current customers while attracting new customers through various methods. Customer churn is a major challenge in different industries and companies. Despite their initial successful attempts at attracting customers, organizations soon face the fact that their current customers may turn away towards their rivals. By identifying churn candidates, organizations will be able to guarantee their future success by revising their customer relationship management policy.Analyzing the data of the telecommunications industries, this study provided an effective early-churn-detection solution using modern techniques by stacking data mining algorithms. Research findings indicate that integrating support vector machines (SVMs) with the chi-square automatic interaction detection (CHAID) decision tree can yield the best outcome. The results show the proper accuracy of the proposed churn prediction solution. In addition, stacking contributed to improved customer churn detection results.

show abstract

Section: Empirical Research Backgroundmentioning

confidence: 99%

A Stacking-Based Data Mining Solution to Customer Churn Prediction

Shabankareh

Nazarian

et al. 2021

Journal of Relationship Marketing

View full text Add to dashboard Cite

show abstract

“…Table 1 list relevant papers and the data mining model/technique applied in them. [4], [5], [6], [7], [12], [13], [14], [16], [17], [22], [23], [25], [26], [27], [28] Decision Tree [3], [4], [6], [9], [10], [11], [12], [13], [14], [16], [19], [25], [28] [11], [13], [18], [19], [20], [23], [28], [29], [30], [31], [ As it is seen in table 1, a list of all reviewed references that have exploited each method is identified. Classes are sorted based on two factors: number of papers in that field and the recency of publication.…”

Section: Literature Reviewmentioning

confidence: 99%

A Comparative Study of Predicting Customer Churn and Lifetime

Adesua¹,

Danquah²,

Longe³

2020

AIMS Research Journal

View full text Add to dashboard Cite

The problem to be investigated in this research is that of predicting customers who are at risk of leaving the company, a term called churn prediction in telecommunication. The aim of this research is to predict customer churn and further focus on creating customer lifetime profiles. These profiles will allow the company to fit their customer base into n categories and make a long estimation on when a customer is potentially going to terminate their service with the company. The research then proceeds to provide a comparative analysis of neural networks and survival analysis in their capabilities of predicting customer churn and lifetime. . Key words: GSM networks, Base station, Mobile station, Signal strength, GSM service provider

show abstract

“…The first is to understand its triggering forces for which hypothesized influence of antecedents on customer churning is investigated through customer data available from service providers or through self-report surveys (Ahn et al , 2006; Eshghi et al , 2006; Hejazinia and Kazemi, 2014; Kim and Yoon, 2004; Kisioglu and Topcu, 2011; Oghojafor et al , 2012; Portela and Menezes, 2010; Wong, 2011). The second approach is to develop prediction models of customer behaviors (Coussement and De Bock, 2013; Coussement et al , 2010; Glady et al , 2009; Gorgoglione and Panniello, 2011; Gürsoy 2010; Hadden et al , 2005; Hou and Tang, 2010; Huang et al , 2010; Huang et al , 2012; Jahromi et al , 2014; Jamal and Bucklin, 2006; Lariviere and Van den Poel, 2004; Lin et al , 2011; Migueis et al , 2012; Neslin et al , 2006; Owczarczuk, 2010; Qi et al , 2009; Richter et al , 2010; Tsai and Chen, 2010; Tsai and Lu, 2009; Verbeke et al , 2011; 2014; Wang et al , 2009; Xia and Jin, 2008; Xiao et al , 2014; Xie et al , 2009; Yu et al , 2011; Zhang et al , 2012). They use various data mining techniques to compare predictive performance of models derived, to develop new prediction models or to compute the probability of customer defections through simulations.…”

Section: Theoretical Background and Literature Reviewmentioning

confidence: 99%

Understanding IPTV churning behaviors: focus on users in South Korea

Kim¹,

Kim

Park

2017

APJIE

View full text Add to dashboard Cite

Purpose-This study aims to investigate customers' churning out of Internet Protocol Television (IPTV) service, one of the most prevalent forms of IT convergence. Design/methodology/approach-Based on the review of current literature, a research model is introduced to depict the effects of select independent variables on customer churning behavior. First of all, the two groups are compared in terms of predictor variables, including switching barriers, voice of customer (VOC), membership period and degree of contents usage. Then, a curvilinear regression was applied to understand the association relationship between the level of IPTV contents usage and variables of switching barriers, VOC and membership period. Third, a logit regression was performed to predict customer churning through the variables of switching barriers, VOC, membership period and level of IPTV contents usage. Findings-Through the empirical analysis, this study analyzed the factors affecting customer churning behavior of IPTV service providers based on switching barriers, VOC and contents usage. Originality/value-Although several studies on IPTV have been undertaken globally, they have largely depended on self-reporting surveys to examine dynamics between antecedent variables and IPTV performance in terms of customer satisfaction, usage intension and customer retention. This empirical study is performed to understand influential factors of IPTV service defection through the weblog analysis of 3,906 service users, who represented both service defectors and non-defectors during a specific month.

show abstract

A recommender system to avoid customer churn: A case study

Cited by 31 publications

References 21 publications

A Stacking-Based Data Mining Solution to Customer Churn Prediction

A Stacking-Based Data Mining Solution to Customer Churn Prediction

A Comparative Study of Predicting Customer Churn and Lifetime

Understanding IPTV churning behaviors: focus on users in South Korea

Contact Info

Product

Resources

About