Pre-processing of E-Commerce Data for Customer Churn Prediction using Data Mining

Due to competition between online retailers, the need for providing improved customer service has grown rapidly. In addition to reduction in sales due to loss of customers, more investments are needed to be done to attract new customers. Companies now are working continuously to improve their perceived quality by way of giving timely and quality service to their customers. Customer churn has become one of the primary challenges that many firms are facing nowadays. Several churn prediction models and techniques are proposed previously in literature to predict customer churn in areas such as finance, telecom, banking etc. Researchers are also working on customer churn prediction in e-commerce using data mining and machine learning techniques. In this paper, a comprehensive review of various models to predict customer churn in e-commerce data mining and machine learning techniques has been presented. A critical review of recent research papers in the field of customer churn prediction in e-commerce using data mining has been done. Thereafter, important inferences and research gaps after studying the literature are presented. Finally, the research significance and concluding remarks are described in the end.

Download Full-text

Customer Churn Prediction in Telecommunication Industry Using Data Mining Methods

Innovaciencia Facultad de Ciencias Exactas Físicas y Naturales ◽

10.15649/2346075x.999 ◽

2020 ◽

Vol 8 (1) ◽

pp. 1-8

Author(s):

Homa Meghyasi ◽

Abas Rad

Keyword(s):

Neural Network ◽

Data Mining ◽

Genetic Algorithm ◽

Churn Prediction ◽

Modular Neural Network ◽

Customer Churn ◽

Important Challenge ◽

Accuracy Result ◽

Customer Churn Prediction ◽

Using Data

At present, in competitive space between companies and organizations, customers churn is their most important challenge. When a customer becomes churn, organizations lose one of their most important assets, which can lead to financial losses and even bankruptcy. Customer churn prediction using data mining techniques can alleviate these problems to some extent. The aim of the present study is to provide a hybrid method based on Genetic Algorithm and Modular Neural Network to customer churn prediction in telecommunication industries and use Irancell data as a sample. The accuracy result of this study which is 95.5% get the highest accuracy rank in comparisons with the result of other methods, which shows using modular neural network with two modules of feedforward neural network and also using genetic algorithm to obtain optimal structure for modules of the neural network are the most important indicators of this method to each the highest accuracy result among the rest of methods.

Download Full-text

Data Mining Techniques in Customer Churn Prediction

Recent Patents on Computer Science ◽

10.2174/1874479611003010028 ◽

2010 ◽

Vol 3 (1) ◽

pp. 28-32 ◽

Cited By ~ 1

Author(s):

Chih-Fong Tsai ◽

Yu-Hsin Lu

Keyword(s):

Data Mining ◽

Churn Prediction ◽

Data Mining Techniques ◽

Customer Churn ◽

Customer Churn Prediction

Download Full-text

Predicting customer churn in mobile industry using data mining technology

Industrial Management & Data Systems ◽

10.1108/imds-12-2015-0509 ◽

2017 ◽

Vol 117 (1) ◽

pp. 90-109 ◽

Cited By ~ 16

Author(s):

Eui-Bang Lee ◽

Jinwha Kim ◽

Sang-Gun Lee

Keyword(s):

Data Mining ◽

Decision Tree ◽

Online News ◽

Partial Least Square ◽

Churn Prediction ◽

Mining Technology ◽

Content Type ◽

Customer Churn ◽

Mobile Industry ◽

Using Data

Purpose The purpose of this paper is to identify the influence of the frequency of word exposure on online news based on the availability heuristic concept. So that this is different from most churn prediction studies that focus on subscriber data. Design/methodology/approach This study examined the churn prediction through words presented the previous studies and additionally identified words what churn generate using data mining technology in combination with logistic regression, decision tree graphing, neural network models, and a partial least square (PLS) model. Findings This study found prediction rates similar to those delivered by subscriber data-based analyses. In addition, because previous studies do not clearly suggest the effects of the factors, this study uses decision tree graphing and PLS modeling to identify which words deliver positive or negative influences. Originality/value These findings imply an expansion of churn prediction, advertising effect, and various psychological studies. It also proposes concrete ideas to advance the competitive advantage of companies, which not only helps corporate development, but also improves industry-wide efficiency.

Download Full-text