Customer Churn Analysis and Prediction Using Data Mining Models in Banking Industry

Ketut Gde Manik Karvana, Setiadi Yazid, Amril Syalim, Petrus Mursanto

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

29 Citations (Scopus)

Abstract

A new method for customer churn analysis and prediction has been proposed. The method uses data mining model in banking industries. This has been inspired by the fact that there are around 1,5 million churn customers in a year which is increasing every year. Churn customer prediction is an activity carried out to predict whether the customer will leave the company or not. One way to predict this customer churn is to use a classification technique from data mining that produces a machine learning model. This study tested 5 different classification methods with a dataset consisting of 57 attributes. Experiments were carried out several times using comparisons between different classes. Support Vector Machine (SVM) with a comparison of 50:50 Class sampling data is the best method for predicting churn customers at a private bank in Indonesia. The results of this modeling can be utilized by company who will apply strategic action to prevent customer churn.

Original languageEnglish
Title of host publication2019 International Workshop on Big Data and Information Security, IWBIS 2019
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages33-38
Number of pages6
ISBN (Electronic)9781728153476
DOIs
Publication statusPublished - Oct 2019
Event2019 International Workshop on Big Data and Information Security, IWBIS 2019 - Bali, Indonesia
Duration: 11 Oct 2019 → …

Publication series

Name2019 International Workshop on Big Data and Information Security, IWBIS 2019

Conference

Conference2019 International Workshop on Big Data and Information Security, IWBIS 2019
Country/TerritoryIndonesia
CityBali
Period11/10/19 → …

Keywords

  • classification
  • customer churn
  • data mining
  • machine learning
  • prediction

Fingerprint

Dive into the research topics of 'Customer Churn Analysis and Prediction Using Data Mining Models in Banking Industry'. Together they form a unique fingerprint.

Cite this