A Prediction Model of Customer Churn considering Customer Value: An Empirical Research of Telecom Industry in China
TL;DR: Wang et al. as discussed by the authors analyzed the trends and causes of customer churn through data mining algorithms, and gave the answers to such questions as how the customer churn occurs, the influencing factors of user churn, and how enterprises win back churned customers.
Abstract: Customer churn will cause the value flowing from customers to enterprises to decrease. If customer churn continues to occur, the enterprise will gradually lose its competitive advantage. When the growth of new customers cannot meet the needs of enterprise development, the enterprise will fall into a survival dilemma. Focusing on the customer churn prediction model, this paper takes the telecom industry in China as the research object, establishes a customer churn prediction model by using a logistic regression algorithm based on the big data of high-value customer operation in the telecom industry, effectively identifies the potential churned customers, and then puts forward targeted win-back strategies according to the empirical research results. This paper analyzes the trends and causes of customer churn through data mining algorithms and gives the answers to such questions as how the customer churn occurs, the influencing factors of customer churn, and how enterprises win back churned customers. The results of this paper can better serve the practice of customer relationship management in the telecom industry and provide a reference for the telecom industry to identify high-risk churned customers in advance, enhance customer loyalty and viscosity, maintain “high-value” customers, and continue to provide customers with “value” and reduce the cost of maintaining customers.
Citations
More filters
TL;DR: A churn prediction model based on the combination of k-means clustering and AdaBoost classifier algorithm, allowing the segmentation of customers into three categories is proposed, showing that the research method of clustering before prediction can improve prediction accuracy.
Abstract: In customer relationship management, it is important for e-commerce businesses to attract new customers and retain existing ones. Research on customer churn prediction using AI technology is now a major part of e-commerce management. This paper proposes a churn prediction model based on the combination of k-means clustering and AdaBoost classifier algorithm, allowing the segmentation of customers into three categories. Important customer groups can also be determined based on customer behavior and temporal data. Customer churn prediction was carried out using AdaBoost classification and BP neural network techniques. The results show that the research method of clustering before prediction can improve prediction accuracy. In addition, a comparative analysis of the results suggests that the AdaBoost model has better prediction accuracy than the BP neural network model. The research results of this paper can help B2C e-commerce companies develop customer retention measures and marketing strategies.
3 citations
01 Jan 2006
TL;DR: In this paper, the authors present a competing risk model that considers the characteristics of a customer in order to predict the customer's life under the number portability system, and three competing risks considered are pricing policy, quality of communication, and usefulness of service.
Abstract: Since Korean government has implemented the "Number Portability System" in the domestic mobile communications market, mobile communication companies have been striving to hold onto existing customers and at the same time to attract new customers. This paper presents a competing risk model that considers the characteristics of a customer in order to predict the customer's life under the "Number Portability System." Three competing risks considered are pricing policy, quality of communication, and usefulness of service. It was observed that the customers who pay more are less sensitive on pricing policy younger people are less sensitive than older people to the quality of communication and women are more sensitive than men to the degree of usefulness of service. We expect that the result of this study can be used as a guideline for effective management of mobile phone customers under the Number Portability System.
3 citations
Journal Article•
TL;DR: The upgrade of IT and market and customer positioning technology brought by that provides enterprises with more opportunities of cross-selling as mentioned in this paper, providing customers with customized products, meeting customers' requirements and occupying more market by cross selling will be beneficial to the enterprises to gain the absolute advantages by reducing prices.
Abstract: Cross-selling is a kind of selling practice providing value for both customers and enterprises.The upgrade of IT and market and customer positioning technology brought by that provides enterprises with more opportunities of cross-selling.Providing customers with customized products,meeting customers' requirements and occupying more market by cross-selling will be beneficial to the enterprises to gain the absolute advantages by reducing prices.
1 citations
TL;DR: A customer churn early warning system based on data mining is established and the RFT model proposed in the experiment and its results show that customer value is a key factor in the decision-making process of a firm.
Abstract: Customer churn is a fundamental problem faced by enterprises and an important factor affecting the operation of enterprises. Due to current market conditions and changing consumer behavior, it analyzes potential customer behavior trends by mining customer behavior data. This allows companies to set targets for looming market changes so that market movements can be predetermined. The rapid development of modern mobile communication technology makes the way of life need more new ways to adapt to the development of the new era. At the same time, with the rapid development of mobile communication technology, information management systems have been widely used. If a large amount of data can support decision-making information through data mining technology, it can drive the process of enterprise decision-making. It conducts purposeful and differentiated retention efforts on these customers. It increases the success rate of high-value customer retention, reduces the likelihood of customer churn, and reduces maintenance costs. It does this to achieve preset goals and minimize losses due to customer exit. This paper proposes and establishes a customer churn early warning system based on data mining. It uses this to find the customer trends behind a large amount of customer data. It uses the decision tree algorithm to participate in the decision-making process of the enterprise with this algorithm model. The RFT model proposed in the experiment and its results show that customer value is a key factor in the decision-making process of a firm. The accuracy rate is about 6% higher than that of the control group using the logistic regression model directly.
1 citations
TL;DR: In this article , a machine learning algorithm was applied to a large-capacity operating dataset of rental care service in an electronics company in Korea, to learn meaningful features and develop and verify the churn prediction model.
Abstract: Abstract Customer churn is a major issue for large enterprises. In particular, in the rental business sector, companies are looking for ways to retain their customers because they are their main source of revenue. The main contribution of our work is to analyze the customer behavior information of actual water purifier rental company, where customer churn occurs very frequently, and to develop and verify the churn prediction model. A machine learning algorithm was applied to a large-capacity operating dataset of rental care service in an electronics company in Korea, to learn meaningful features. To measure the performance of the model, the F-measure and area under curve (AUC) were adopted whereby an F1 value of 93% and an AUC of 88% were achieved. The dataset containing approximately 84,000 customers was used for training and testing. Another contribution was to evaluate the inference performance of the predictive model using the contract status of about 250,000 customer data currently in operation, confirming a hit rate of about 80%. Finally, this study identified and calculated the influence of key variables on individual customer churn to enable a business person (rental care customer management staff) to carry out customer-tailored marketing to address the cause of the churn.
References
More filters
Journal Article•
TL;DR: Defection rates are not just a measure of service quality; they are also a guide for achieving it; by listening to the reasons why customers defect, managers learn exactly where the company is falling short and where to direct their resources.
Abstract: Companies that want to improve their service quality should take a cue from manufacturing and focus on their own kind of scrap heap: customers who won't come back. Because that scrap heap can be every bit as costly as broken parts and misfit components, service company managers should strive to reduce it. They should aim for "zero defections"--keeping every customer they can profitably serve. As companies reduce customer defection rates, amazing things happen to their financials. Although the magnitude of the change varies by company and industry, the pattern holds: profits rise sharply. Reducing the defection rate just 5% generates 85% more profits in one bank's branch system, 50% more in an insurance brokerage, and 30% more in an auto-service chain. And when MBNA America, a Delaware-based credit card company, cut its 10% defection rate in half, profits rose a whopping 125%. But defection rates are not just a measure of service quality; they are also a guide for achieving it. By listening to the reasons why customers defect, managers learn exactly where the company is falling short and where to direct their resources. Staples, the stationery supplies retailer, uses feedback from customers to pinpoint products that are priced too high. That way, the company avoids expensive broad-brush promotions that pitch everything to everyone. Like any important change, managing for zero defections requires training and reinforcement. Great-West Life Assurance Company pays a 50% premium to group health-insurance brokers that hit customer-retention targets, and MBNA America gives bonuses to departments that hit theirs.
5,915 citations
Journal Article•
2,686 citations
"A Prediction Model of Customer Chur..." refers background in this paper
...Jones and Sasser’s [4] research shows that when the customer churn rate of an enterprise decreases by 5%, the average profit rate of the enterprise will increase by 25%– 85%....
[...]
TL;DR: In this paper, the authors investigate the differential effects of customer relationship perceptions and relationship marketing instruments on customer retention and customer share development over time, and show that affective commitment and loyalty programs that provide economic incentives positively affect both customer retention, whereas direct mailings influence customer share.
Abstract: Scholars have questioned the effectiveness of several customer relationship management strategies. The author investigates the differential effects of customer relationship perceptions and relationship marketing instruments on customer retention and customer share development over time. Customer relationship perceptions are considered evaluations of relationship strength and a supplier’s offerings, and customer share development is the change in customer share between two periods. The results show that affective commitment and loyalty programs that provide economic incentives positively affect both customer retention and customer share development, whereas direct mailings influence customer share development. However, the effect of these variables is rather small. The results also indicate that firms can use the same strategies to affect both customer retention and customer share development.
1,460 citations
"A Prediction Model of Customer Chur..." refers background in this paper
...Verhoef [29] and Reinartz and Kumar [30] believed that user characteristics are also the main factors affecting customer churn, and Reinartz and Kumar [30] found that user statistics, such as consumption level and personal income, can affect the churn rate....
[...]
TL;DR: In this paper, the conditions under which a loyalty rewards program will have a positive effect on customer evaluations, behavior, and repeat purchase intentions were investigated in a worldwide financial services company that offers a loyalty reward program.
Abstract: Companies that offer loyalty reward programs believe that their programs have a long-run positive effect on customer evaluations and behavior. However, if loyalty rewards programs increase relationship durations and usage levels, customers will be increasingly exposed to the complete spectrum of service experiences, including experiences that may cause customers to switch to another service provider. Using cross-sectional, time-series data from a worldwide financial services company that offers a loyalty reward program, this article investigates the conditions under which a loyalty rewards program will have a positive effect on customer evaluations, behavior, and repeat purchase intentions. The results show that members in the loyalty reward program overlook or discount negative evaluations of the company vis-a-vis competion. One possible reason could be that members of the loyalty rewards program perceive that they are getting better quality and service for their price or, in other words, “good value.”
1,197 citations
"A Prediction Model of Customer Chur..." refers background in this paper
...According to the summary of the main influencing variables of customer churn in recent years, it is found that scholars’ research on influencing factors of customer churn in the telecom industry mainly focuses on three aspects: first, consumption-related variables, such as call duration [27] and consumption amount [27, 28], followed by customer statistical variables [29–31], including identity information and age [32, 33], customer income [33, 34], and customer satisfaction [35, 36], and finally enterprise-related variables, such as enterprise channel operation ability [37] and purchase of related products [38]....
[...]
TL;DR: In this article, the authors developed a framework that incorporates projected profitability of customers in the computation of lifetime duration and identified factors under a manager's control that explain the variation in the profitable lifetime duration.
Abstract: The authors develop a framework that incorporates projected profitability of customers in the computation of lifetime duration. Furthermore, the authors identify factors under a manager’s control that explain the variation in the profitable lifetime duration. They also compare other frameworks with the traditional methods such as the recency, frequency, and monetary value framework and past customer value and illustrate the superiority of the proposed framework. Finally, the authors develop several key implications that can be of value to decision makers in managing customer relationships.
1,161 citations