DSpace Repository

An Intelligent System for Churn Prediction and Customer Retention: The Case of a Telecommunications Company

Show simple item record

dc.contributor.advisor Esichaikul, Dr. Vatcharaporn
dc.contributor.author Sarangi, Parth
dc.contributor.other Dailey, Dr. Matthew N.
dc.contributor.other Guha, Prof. Sumanta
dc.date.accessioned 2018-05-03T08:55:04Z
dc.date.available 2018-05-03T08:55:04Z
dc.date.issued 2018-05
dc.identifier.issn Other and AIT
dc.identifier.uri http://www.cs.ait.ac.th/xmlui/handle/123456789/891
dc.description 85 p en_US
dc.description.abstract The telecommunications industry is very competitive in most of the developed and developing countries. A few companies operate to provide numerous services to a huge consumer base. Rapid technological advancements in the ICT sector has increased the availability and afford-ability of mobile telephony devices. With an increasing adoption of mobile telephony devices there is a greater increase in the demand for mobility services. Services such as phone calls, sms, internet etc., have increased over the past decade. With the growing demand and growing consumer base, services providers have reduced prices of these services. Profitability of companies is decided by the number of consumers. In these highly competitive market, customer satisfaction and retention is of high importance. In this study an intelligent churn prediction and customer retention (ICPCR) system is developed. An open source dataset of call detail records (CDR), with 5000 records and 21 features is selected for purpose of system design and model development. Eight data mining methods are employed to generate prediction models. Prediction models such as decision tree, random forest, support vector machines, neural networks and naive bayes are compared for performance and evaluated based on accuracy, sensitivity, specificity and positive prediction metrics. Based on the performance decision tree is selected as the prediction engine in implementation of ICPCR. The customer retention system is designed on decision table rules and up-selling techniques are suggested for every customer predicted as churner. This study is designed to facilitate the customer service representative with a mechanism to visualize customer call detail data. In addition, it also enables them to predict the churning status of current customers, and also presents them with an option to control churning by suggesting marketing solutions or product benefits. This study presents a web based approach with KPI dashboards, charts and maps, OALP for roll-up and drill-down analysis, prediction and finally retention strategies for controlling customer churn. en_US
dc.description.sponsorship AIT Fellowship en_US
dc.language.iso en_US en_US
dc.publisher AIT en_US
dc.subject churn en_US
dc.subject customer en_US
dc.subject prediction en_US
dc.subject retention en_US
dc.subject intelligent en_US
dc.subject data mining en_US
dc.subject decision tree en_US
dc.title An Intelligent System for Churn Prediction and Customer Retention: The Case of a Telecommunications Company en_US
dc.type Thesis en_US

Files in this item

This item appears in the following Collection(s)

Show simple item record

Search DSpace

Advanced Search


My Account