Search results

1 – 10 of over 2000
To view the access options for this content please click here
Article
Publication date: 13 March 2017

Samira Khodabandehlou and Mahmoud Zivari Rahman

This paper aims to provide a predictive framework of customer churn through six stages for accurate prediction and preventing customer churn in the field of business.

Abstract

Purpose

This paper aims to provide a predictive framework of customer churn through six stages for accurate prediction and preventing customer churn in the field of business.

Design/methodology/approach

The six stages are as follows: first, collection of customer behavioral data and preparation of the data; second, the formation of derived variables and selection of influential variables, using a method of discriminant analysis; third, selection of training and testing data and reviewing their proportion; fourth, the development of prediction models using simple, bagging and boosting versions of supervised machine learning; fifth, comparison of churn prediction models based on different versions of machine-learning methods and selected variables; and sixth, providing appropriate strategies based on the proposed model.

Findings

According to the results, five variables, the number of items, reception of returned items, the discount, the distribution time and the prize beside the recency, frequency and monetary (RFM) variables (RFMITSDP), were chosen as the best predictor variables. The proposed model with accuracy of 97.92 per cent, in comparison to RFM, had much better performance in churn prediction and among the supervised machine learning methods, artificial neural network (ANN) had the highest accuracy, and decision trees (DT) was the least accurate one. The results show the substantially superiority of boosting versions in prediction compared with simple and bagging models.

Research limitations/implications

The period of the available data was limited to two years. The research data were limited to only one grocery store whereby it may not be applicable to other industries; therefore, generalizing the results to other business centers should be used with caution.

Practical implications

Business owners must try to enforce a clear rule to provide a prize for a certain number of purchased items. Of course, the prize can be something other than the purchased item. Business owners must accept the items returned by the customers for any reasons, and the conditions for accepting returned items and the deadline for accepting the returned items must be clearly communicated to the customers. Store owners must consider a discount for a certain amount of purchase from the store. They have to use an exponential rule to increase the discount when the amount of purchase is increased to encourage customers for more purchase. The managers of large stores must try to quickly deliver the ordered items, and they should use equipped and new transporting vehicles and skilled and friendly workforce for delivering the items. It is recommended that the types of services, the rules for prizes, the discount, the rules for accepting the returned items and the method of distributing the items must be prepared and shown in the store for all the customers to see. The special services and reward rules of the store must be communicated to the customers using new media such as social networks. To predict the customer behaviors based on the data, the future researchers should use the boosting method because it increases efficiency and accuracy of prediction. It is recommended that for predicting the customer behaviors, particularly their churning status, the ANN method be used. To extract and select the important and effective variables influencing customer behaviors, the discriminant analysis method can be used which is a very accurate and powerful method for predicting the classes of the customers.

Originality/value

The current study tries to fill this gap by considering five basic and important variables besides RFM in stores, i.e. prize, discount, accepting returns, delay in distribution and the number of items, so that the business owners can understand the role services such as prizes, discount, distribution and accepting returns play in retraining the customers and preventing them from churning. Another innovation of the current study is the comparison of machine-learning methods with their boosting and bagging versions, especially considering the fact that previous studies do not consider the bagging method. The other reason for the study is the conflicting results regarding the superiority of machine-learning methods in a more accurate prediction of customer behaviors, including churning. For example, some studies introduce ANN (Huang et al., 2010; Hung and Wang, 2004; Keramati et al., 2014; Runge et al., 2014), some introduce support vector machine ( Guo-en and Wei-dong, 2008; Vafeiadis et al., 2015; Yu et al., 2011) and some introduce DT (Freund and Schapire, 1996; Qureshi et al., 2013; Umayaparvathi and Iyakutti, 2012) as the best predictor, confusing the users of the results of these studies regarding the best prediction method. The current study identifies the best prediction method specifically in the field of store businesses for researchers and the owners. Moreover, another innovation of the current study is using discriminant analysis for selecting and filtering variables which are important and effective in predicting churners and non-churners, which is not used in previous studies. Therefore, the current study is unique considering the used variables, the method of comparing their accuracy and the method of selecting effective variables.

Details

Journal of Systems and Information Technology, vol. 19 no. 1/2
Type: Research Article
ISSN: 1328-7265

Keywords

To view the access options for this content please click here
Article
Publication date: 8 April 2014

Kristof Coussement

Retailers realize that customer churn detection is a critical success factor. However, no research study has taken into consideration that misclassifying a customer as a…

Abstract

Purpose

Retailers realize that customer churn detection is a critical success factor. However, no research study has taken into consideration that misclassifying a customer as a non-churner (i.e. predicting that (s)he will not leave the company, while in reality (s)he does) results in higher costs than predicting that a staying customer will churn. The aim of this paper is to examine the prediction performance of various cost-sensitive methodologies (direct minimum expected cost (DMECC), metacost, thresholding and weighting) that incorporate these different costs of misclassifying customers in predicting churn.

Design/methodology/approach

Cost-sensitive methodologies are benchmarked on six real-life churn datasets from the retail industry.

Findings

This article argues that total misclassification cost, as a churn prediction evaluation measure, is crucial as input for optimizing consumer decision making. The practical classification threshold of 0.5 for churn probabilities (i.e. when the churn probability is greater than 0.5, the customer is predicted as a churner, and otherwise as a non-churner) offers the worst performance. The provided managerial guidelines suggest when to use each cost-sensitive method, depending on churn levels and the cost level discrepancy between misclassifying churners versus non-churners.

Practical implications

This research emphasizes the importance of cost-sensitive learning to improve customer retention management in the retail context.

Originality/value

This article is the first to use the concept of misclassification costs in a churn prediction setting, and to offer recommendations about the circumstances in which marketing managers should use specific cost-sensitive methodologies.

Details

European Journal of Marketing, vol. 48 no. 3/4
Type: Research Article
ISSN: 0309-0566

Keywords

To view the access options for this content please click here
Article
Publication date: 4 June 2010

Steffen Zorn, Wade Jarvis and Steve Bellman

As acquiring new customers is costly, putting effort into satisfying and keeping customers over the long term can improve profitability. Firms usually do not know how each…

Abstract

Purpose

As acquiring new customers is costly, putting effort into satisfying and keeping customers over the long term can improve profitability. Firms usually do not know how each individual customer is feeling at any time (their attitude to the firm), so typically a customer's likelihood of leaving (“churning”) is predicted from behavioural data. The purpose of this paper is to investigate how a firm can add attitudinal variables to these churning models by deriving proxy indicators of satisfaction and commitment from behavioural data. The paper tests whether adding these proxies improved predictions of churning compared to a typical model based on purchasing behaviour (PB).

Design/methodology/approach

Analysing data from 6,000 regular customers from an Australian digital versatile disc rental company, logistic regression predicted membership termination (i.e. churning=1) versus continuation (=0). A baseline model used three traditional behavioural variables directly linked to members' PB. A second model including proxies for satisfaction and commitment from the customer database was compared against the baseline model to investigate improvement in churn prediction.

Findings

The most significant predictor of churn is an indicator of commitment: the uncertainty of a customer's commitment, indicated by number of times they changed their subscription plan.

Practical implications

The more customers change their plan, the more likely they are to quit the relationship with the firm, most likely because they are uncertain about how they can benefit from a long‐term commitment to the firm. Monitoring uncertainty indicators, such as plan changing, allows firms to intervene with special offers for uncertain customers, and, therefore, increase the likelihood of them staying with the firm.

Originality/value

The paper discusses the use of customer behaviour recorded in databases to identify proxy indicators of attitude before this attitude translates into churning behaviour.

Details

Journal of Research in Interactive Marketing, vol. 4 no. 2
Type: Research Article
ISSN: 2040-7122

Keywords

To view the access options for this content please click here
Article
Publication date: 16 March 2012

M. Geetha and Jensolin Abitha Kumari

The purpose of this paper is to provide a detailed analysis of the usage pattern of non‐revenue earning customers (NREC) who cause revenue churn in the company and are…

Abstract

Purpose

The purpose of this paper is to provide a detailed analysis of the usage pattern of non‐revenue earning customers (NREC) who cause revenue churn in the company and are susceptible to churn in the near future. These NREC customers were analyzed to discern a pattern in their usage and to serve as proactive measure to prevent customer churn.

Design/methodology/approach

Data from a leading telecom service provider were analyzed. The company has around seven lakh consumer mobile users. Within the seven lakhs consumer mobile users around two lakh customers are active users, i.e. revenue earning customers. This group of active customers also consists of around 37,388 customers who move to dormant state (from revenue earning to non‐revenue earning) every month. These customers were analyzed to understand their susceptibility to churn.

Findings

Analysis of revenue dump data indicates consumers with overall usage revenue per minute greater than 75 paise (USD 0.01) and those with greater usage of value added services are susceptible to churn. Also based on the nature of calls, churn occurs with the subscribers making more calls to other networks rather than to the same network.

Research limitations/implications

In a fiercely competitive market, service providers constantly focus on customer retention. The study has high importance as it helps to find out the customers who are likely to churn. This would help telecom companies create proactive rather than reactive strategies toward customer churn.

Originality/value

Earlier studies identified the reasons for customer churn and attributed the same to it. The authors propose that prior to customer churn there is a distinct shift in his/her usage pattern with the current service provider and this behavior is termed revenue churn. This revenue churn ultimately leads to customer churn from the network. This revenue churn is not explored much in detail in the literature.

To view the access options for this content please click here
Article
Publication date: 12 November 2020

Jishnu Bhattacharyya and Manoj Kumar Dash

The purpose of this paper is to investigate the distinct reasons and more common reasons that reduce customer satisfaction and are antecedents to customer churn behavior…

Abstract

Purpose

The purpose of this paper is to investigate the distinct reasons and more common reasons that reduce customer satisfaction and are antecedents to customer churn behavior in the telecommunication industry.

Design/methodology/approach

The study adopted the netnography approach to investigate churn behavior by utilizing online user-generated content in qualified social media communities.

Findings

The investigation revealed that “data speed issue”, “ineffective relationship building”, “service area coverage issues” and “billing issues” are some of the most important attributes that influence a consumers' decision to churn. Further, the churn consequence influencers model summarizes the attributes that contribute to overall dissatisfaction and finally results in churn behavior. The study found out the application of the netnography approach in a quantitatively dominant research area and stands out with its insights from a rich qualitative data.

Practical implications

Proper clarification of customer expectations and pain points can help reduce customer churn. The study will serve as the basis for developing future churn prediction models that will contribute to the informed decision-making process.

Originality/value

Contributing to research on customer churn behavior, the study offers a novel attempt to study customer satisfaction and customer churn behavior jointly. The paper is the first attempt that contributes to the extant literature by adopting the unique qualitative approach to understand the reasons for telecommunication churn behavior in the emerging Indian market. Another contribution of this research is that the paper shifts the focus of the electronic word-of-mouth (eWOM) literature to the telecommunications industry, thus adding another block to ongoing research in eWOM communication.

Peer review

The peer review history for this article is available at: https://publons.com/publon/10.1108/ OIR-02-2020-0048

Details

Online Information Review, vol. 45 no. 1
Type: Research Article
ISSN: 1468-4527

Keywords

To view the access options for this content please click here
Article
Publication date: 27 August 2014

Yuangen Lai and Jianxun Zeng

The purpose of this paper is to discuss issues related to customer churn behavior in digital libraries (DLs) and demonstrate the successful application of Survival…

Abstract

Purpose

The purpose of this paper is to discuss issues related to customer churn behavior in digital libraries (DLs) and demonstrate the successful application of Survival Analysis for understanding customer churn status and relationship duration distribution between customers and libraries.

Design/methodology/approach

The study applies non-parametric methods of Survival Analysis to analyze churn behaviors of 8,054 customers from a famous Chinese digital library, and a cluster method to make customer segmentation according to customer behavioral features.

Findings

The customer churn rate of the given library is very high, so as to the churn hazard in early three months after customer's registration on the web site of the library. There is clear difference in both customer survival time and churn hazard among customer groups. It is necessary to strengthen customer churn analysis and customer relationship management (CRM) for DLs.

Research limitations/implications

The studied samples are mainly based on customers from one digital library and some hypotheses have not been strictly proven due to the absence of relevant empirical researches.

Practical implications

This study provides a reasonable basis for decision making about CRM in DLs.

Originality/value

Most previous researches about information behavior concentrate on information seeking behavior in DLs, seldom discuss customer switching behavior. The paper discusses issues related to customer churn analysis and illustrates the adaptation of Survival Analysis to understand customer churn status and relationship duration distribution in DLs.

Details

Program, vol. 48 no. 4
Type: Research Article
ISSN: 0033-0337

Keywords

To view the access options for this content please click here
Article
Publication date: 26 July 2013

Gunnvald B. Svendsen and Nina K. Prebensen

The present paper aims to investigate the effect of network provider, customer demographics, customer satisfaction and perceived switch costs on churn in the mobile…

Abstract

Purpose

The present paper aims to investigate the effect of network provider, customer demographics, customer satisfaction and perceived switch costs on churn in the mobile telecommunications market.

Design/methodology/approach

The study is carried out as a longitudinal, two-wave study of mobile telecommunications customers in Norway: n=1,499 (wave 1) and n=976 (wave 2). Churn is measured as change in the mobile network provider between the two waves. The data are analysed as a logistic regression with the independent variables provider, gender, satisfaction, switch costs and age.

Findings

The analysis shows significant effects of provider, satisfaction, switch costs and age and of the interaction between satisfaction and provider. Gender has no significant effect on churn. Provider effects are interpreted as effects of brand image since other known influences on churn (satisfaction, switch costs and demographics) have been controlled for in the design.

Research limitations/implications

Further research is necessary in order to single out which brand aspects are responsible for the effects of brand ownership and to ensure the generality of the findings outside Scandinavia.

Practical implications

The findings indicate that a strong brand image makes a company less susceptible to customer churn caused by low satisfaction.

Originality/value

The relation between brand ownership and churn in the mobile telecommunications sector has not been reported previously.

Details

European Journal of Marketing, vol. 47 no. 8
Type: Research Article
ISSN: 0309-0566

Keywords

To view the access options for this content please click here
Article
Publication date: 20 August 2019

Sandhya N., Philip Samuel and Mariamma Chacko

Telecommunication has a decisive role in the development of technology in the current era. The number of mobile users with multiple SIM cards is increasing every second…

Abstract

Purpose

Telecommunication has a decisive role in the development of technology in the current era. The number of mobile users with multiple SIM cards is increasing every second. Hence, telecommunication is a significant area in which big data technologies are needed. Competition among the telecommunication companies is high due to customer churn. Customer retention in telecom companies is one of the major problems. The paper aims to discuss this issue.

Design/methodology/approach

The authors recommend an Intersection-Randomized Algorithm (IRA) using MapReduce functions to avoid data duplication in the mobile user call data of telecommunication service providers. The authors use the agent-based model (ABM) to predict the complex mobile user behaviour to prevent customer churn with a particular telecommunication service provider.

Findings

The agent-based model increases the prediction accuracy due to the dynamic nature of agents. ABM suggests rules based on mobile user variable features using multiple agents.

Research limitations/implications

The authors have not considered the microscopic behaviour of the customer churn based on complex user behaviour.

Practical implications

This paper shows the effectiveness of the IRA along with the agent-based model to predict the mobile user churn behaviour. The advantage of this proposed model is as follows: the user churn prediction system is straightforward, cost-effective, flexible and distributed with good business profit.

Originality/value

This paper shows the customer churn prediction of complex human behaviour in an effective and flexible manner in a distributed environment using Intersection-Randomized MapReduce Algorithm using agent-based model.

Details

Data Technologies and Applications, vol. 53 no. 3
Type: Research Article
ISSN: 2514-9288

Keywords

To view the access options for this content please click here
Article
Publication date: 1 December 2001

Miguel A.P.M. Lejeune

Churn management is a fundamental concern for businesses and the emergence of the digital economy has made the problem even more acute. Companies’ initiatives to handle…

Abstract

Churn management is a fundamental concern for businesses and the emergence of the digital economy has made the problem even more acute. Companies’ initiatives to handle churn and customers’ profitability issues have been directed to more customer‐oriented strategies. In this paper, we present a customer relationship management framework based on the integration of the electronic channel. This framework is constituted of four tools that should provide an appropriate collection, treatment and analysis of data. From this perspective, we pay special attention to some of the latest data mining developments which, we believe, are destined to play a central role in churn management. Relying on sensitivity analysis, we propose an analysis framework able to prefigure the possible impact induced by the ongoing data mining enhancements on churn management and on the decision‐making process.

Details

Internet Research, vol. 11 no. 5
Type: Research Article
ISSN: 1066-2243

Keywords

To view the access options for this content please click here
Article
Publication date: 20 May 2021

Muhammad Usman Tariq, Muhammad Babar, Marc Poulin and Akmal Saeed Khattak

The purpose of the proposed model is to assist the e-business to predict the churned users using machine learning. This paper aims to monitor the customer behavior and to…

Abstract

Purpose

The purpose of the proposed model is to assist the e-business to predict the churned users using machine learning. This paper aims to monitor the customer behavior and to perform decision-making accordingly.

Design/methodology/approach

The proposed model uses the 2-D convolutional neural network (CNN; a technique of deep learning). The proposed model is a layered architecture that comprises two different phases that are data load and preprocessing layer and 2-D CNN layer. In addition, the Apache Spark parallel and distributed framework is used to process the data in a parallel environment. Training data is captured from Kaggle by using Telco Customer Churn.

Findings

The proposed model is accurate and has an accuracy score of 0.963 out of 1. In addition, the training and validation loss is extremely less, which is 0.004. The confusion matric results show the true-positive values are 95% and the true-negative values are 94%. However, the false-negative is only 5% and the false-positive is only 6%, which is effective.

Originality/value

This paper highlights an inclusive description of preprocessing required for the CNN model. The data set is addressed more carefully for the successful customer churn prediction.

Details

Journal of Modelling in Management, vol. ahead-of-print no. ahead-of-print
Type: Research Article
ISSN: 1746-5664

Keywords

1 – 10 of over 2000