Performance Comparison of Neural Network Training Algorithms for Modeling Customer Churn Prediction
Predicting customer churn has become the priority of every telecommunication service provider as the market is becoming more saturated and competitive. This paper presents a comparison of neural network learning algorithms for customer churn prediction. The data set used to train and test the neu...
Saved in:
Main Authors: | , , , , |
---|---|
Format: | Conference or Workshop Item |
Language: | English |
Published: |
2017
|
Subjects: | |
Online Access: | http://eprints.unisza.edu.my/1013/1/FH03-FIK-18-12865.pdf http://eprints.unisza.edu.my/1013/ |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
id |
my-unisza-ir.1013 |
---|---|
record_format |
eprints |
spelling |
my-unisza-ir.10132020-11-05T07:11:16Z http://eprints.unisza.edu.my/1013/ Performance Comparison of Neural Network Training Algorithms for Modeling Customer Churn Prediction Mohd Khalid, Awang Mohammad Ridwan, Ismail Mokhairi, Makhtar M Nordin, A Rahman Abd Rasid, Mamat QA76 Computer software Predicting customer churn has become the priority of every telecommunication service provider as the market is becoming more saturated and competitive. This paper presents a comparison of neural network learning algorithms for customer churn prediction. The data set used to train and test the neural network algorithms was provided by one of the leading telecommunication company in Malaysia. The Multilayer Perceptron (MLP) networks are trained using nine (9) types of learning algorithms, which are Levenberg Marquardt backpropagation (trainlm), BFGS Quasi-Newton backpropagation (trainbfg), Conjugate Gradient backpropagation with Fletcher-Reeves Updates (traincgf), Conjugate Gradient backpropagation with Polak-Ribiere Updates (traincgp), Conjugate Gradient backpropagation with Powell-Beale Restarts (traincgb), Scaled Conjugate Gradient backpropagation (trainscg), One Step Secant backpropagation (trainoss), Bayesian Regularization backpropagation (trainbr), and Resilient backpropagation (trainrp). The performance of the Neural Network is measured based on the prediction accuracy of the learning and testing phases. LM learning algorithm is found to be the optimum model of a neural network model consisting of fourteen input units, one hidden node and one output node. The best result of the experiment indicated that this model is able to produce the performance accuracy of 94.82%. 2017 Conference or Workshop Item NonPeerReviewed text en http://eprints.unisza.edu.my/1013/1/FH03-FIK-18-12865.pdf Mohd Khalid, Awang and Mohammad Ridwan, Ismail and Mokhairi, Makhtar and M Nordin, A Rahman and Abd Rasid, Mamat (2017) Performance Comparison of Neural Network Training Algorithms for Modeling Customer Churn Prediction. In: International Conference on Informatics, Computing and Applied Mathematics, 9 January 2017, UNISZA Kampus Gong Badak. |
institution |
Universiti Sultan Zainal Abidin |
building |
UNISZA Library |
collection |
Institutional Repository |
continent |
Asia |
country |
Malaysia |
content_provider |
Universiti Sultan Zainal Abidin |
content_source |
UNISZA Institutional Repository |
url_provider |
https://eprints.unisza.edu.my/ |
language |
English |
topic |
QA76 Computer software |
spellingShingle |
QA76 Computer software Mohd Khalid, Awang Mohammad Ridwan, Ismail Mokhairi, Makhtar M Nordin, A Rahman Abd Rasid, Mamat Performance Comparison of Neural Network Training Algorithms for Modeling Customer Churn Prediction |
description |
Predicting customer churn has become the priority of every telecommunication service
provider as the market is becoming more saturated and competitive. This paper presents a
comparison of neural network learning algorithms for customer churn prediction. The data
set used to train and test the neural network algorithms was provided by one of the leading
telecommunication company in Malaysia. The Multilayer Perceptron (MLP) networks are
trained using nine (9) types of learning algorithms, which are Levenberg Marquardt
backpropagation (trainlm), BFGS Quasi-Newton backpropagation (trainbfg), Conjugate
Gradient backpropagation with Fletcher-Reeves Updates (traincgf), Conjugate Gradient
backpropagation with Polak-Ribiere Updates (traincgp), Conjugate Gradient
backpropagation with Powell-Beale Restarts (traincgb), Scaled Conjugate Gradient
backpropagation (trainscg), One Step Secant backpropagation (trainoss), Bayesian
Regularization backpropagation (trainbr), and Resilient backpropagation (trainrp). The
performance of the Neural Network is measured based on the prediction accuracy of the
learning and testing phases. LM learning algorithm is found to be the optimum model of a
neural network model consisting of fourteen input units, one hidden node and one output
node. The best result of the experiment indicated that this model is able to produce the
performance accuracy of 94.82%. |
format |
Conference or Workshop Item |
author |
Mohd Khalid, Awang Mohammad Ridwan, Ismail Mokhairi, Makhtar M Nordin, A Rahman Abd Rasid, Mamat |
author_facet |
Mohd Khalid, Awang Mohammad Ridwan, Ismail Mokhairi, Makhtar M Nordin, A Rahman Abd Rasid, Mamat |
author_sort |
Mohd Khalid, Awang |
title |
Performance Comparison of Neural Network Training Algorithms
for Modeling Customer Churn Prediction |
title_short |
Performance Comparison of Neural Network Training Algorithms
for Modeling Customer Churn Prediction |
title_full |
Performance Comparison of Neural Network Training Algorithms
for Modeling Customer Churn Prediction |
title_fullStr |
Performance Comparison of Neural Network Training Algorithms
for Modeling Customer Churn Prediction |
title_full_unstemmed |
Performance Comparison of Neural Network Training Algorithms
for Modeling Customer Churn Prediction |
title_sort |
performance comparison of neural network training algorithms
for modeling customer churn prediction |
publishDate |
2017 |
url |
http://eprints.unisza.edu.my/1013/1/FH03-FIK-18-12865.pdf http://eprints.unisza.edu.my/1013/ |
_version_ |
1683234955073683456 |
score |
13.18916 |