Web
Analytics

Customer Decision Prediction Using Deep Neural Network on Telco Customer Churn Data

  Hiya Nalatissifa (1*), Hilman Ferdinandus Pardede (2)

(1) Universitas Nusa Mandiri - Indonesia
(2) Indonesian Institute of Sciences - Indonesia
(*) Corresponding Author

Received: August 02, 2021; Revised: September 27, 2021
Accepted: December 20, 2021; Published: December 31, 2021


How to cite (IEEE): H. Nalatissifa,  and H. F. Pardede, "Customer Decision Prediction Using Deep Neural Network on Telco Customer Churn Data," Jurnal Elektronika dan Telekomunikasi, vol. 21, no. 2, pp. 122-127, Dec. 2021. doi: 10.14203/jet.v21.122-127

Abstract

Customer churn is the most important problem in the business world, especially in the telecommunications industry, because it greatly influences company profits. Getting new customers for a company is much more difficult and expensive than retaining existing customers. Machine learning, part of data mining, is a sub-field of artificial intelligence widely used to make predictions, including predicting customer churn. Deep neural network (DNN) has been used for churn prediction, but selecting hyperparameters in modeling requires more time and effort, making the process more challenging for the researcher. Therefore, the purpose of this study is to propose a better architecture for the DNN algorithm by using a hard tuner to obtain more optimal hyperparameters. The tuning hyperparameter used is random search in determining the number of nodes in each hidden layer, dropout, and learning rate. In addition, this study also uses three variations of the number of hidden layers, two variations of the activation function, namely rectified linear unit (ReLu) and Sigmoid, then uses five variations of the optimizer (stochastic gradient descent (SGD), adaptive moment estimation (Adam), adaptive gradient algorithm (Adagrad), Adadelta, and root mean square propagation (RMSprop)). Experiments show that the DNN algorithm using hyperparameter tuning random search produces a performance value of 83.09 % accuracy using three hidden layers, the number of nodes in each hidden layer is [20, 35, 15], using the RMSprop optimizer, dropout 0.1, the learning rate is 0.01, with the fastest tuning time of 21 seconds. Better than modeling using k-nearest neighbor (K-NN), random forest (RF), and decision tree (DT) as comparison algorithms.

  http://dx.doi.org/10.14203/jet.v21.122-127

Keywords


customer churn; data mining; machine learning; deep neural network

Full Text:

  PDF

References


H. N. Irmanda, R. Astriratma, And S. Afrizal, "Perbandingan Metode Jaringan Syaraf Tiruan Dan Pohon Keputusan Untuk Prediksi Churn," J. Sist. Inf., Vol. 11, No. 2, Pp. 1817–1825, 2019. Crossref

D. R. Chabumba, R. Ajoodha, and A. Jadhav, "Predicting telecommunication customer churn using machine learning techniques," in Proc. Int. Conf. Interdisciplinary Research in Technology and Management, Feb. 2021.

Y. T. Utami, D. A. Shofiana, and Y. Heningtyas, “Penerapan algoritma C4.5 untuk prediksi churn rate pengguna jasa telekomunikasi,” J. Komputasi, vol. 8, no. 2, pp. 69–76, 2020, doi: 10.23960%2Fkomputasi.v8i2.2647. Crossref

Yulianti, “Metode data mining untuk prediksi churn pelanggan,” ICT Akad. Telkom, vol. 9, no. 16, pp. 46–52, 2018.

I. M. M. Mitkees, S. M. Badr, A. I. B. ElSeddawy, “Customer churn prediction model using data mining techniques,” 2017 13th Int. Computer Engineering Conf., 2017, pp. 262–268, DOI: 10.1109/ICENCO.2017.8289798. Crossref

A. S. Halibas, A. C. Matthew, I. G. Pillai, J. H. Reazol, E. G. Delvo, and L. B. Reazol, “Determining the intervening effects of exploratory data analysis and feature engineering in telecoms customer churn modeling,” 2019 4th Middle East College Int. Conf. Big Data Smart City, 2019, doi: 10.1109/ICBDSC.2019.8645578. Crossref

N. W. Wardani et al., “Prediksi customer churn dengan algoritma decision tree C4.5 berdasarkan segmentasi pelanggan untuk mempertahankan pelanggan pada perusahaan retail,” Rekayasa Sist. Komput., vol. 1, no. 1, pp. 16–24, 2018, doi: 10.31598/jurnalresistor.v1i1.219. Crossref

K. Kim and J. Lee, “Bayesian optimization of customer churn predictive model,” 2018 Joint 10th Int. Conf. Soft Comput. Intell. Syst. and 19th Int. Symp. Adv. Intell. Syst., 2018, pp. 85–88, doi: 10.1109/SCIS-SIS.2018.00024. Crossref

A. Roihan, P. A. Sunarya, and A. S. Rafika, “Pemanfaatan machine learning dalam berbagai bidang: Review paper,” Indones. J. Comput. Inf. Technol., vol. 5, no. 1, pp. 75–82, 2020, doi: 10.31294/ijcit.v5i1.7951. Crossref

N. P. H. Oka and A. S. Arifin, “Telecommunication service subscriber churn likelihood prediction analysis using diverse machine learning model,” 2020 3rd Int. Conf. Mechanical, Electronics, Computer, and Industrial Technology, 2020, pp. 24-29, doi: 10.1109/MECnIT48290.2020.9166584. Crossref

E. Domingos, B. Ojeme, and O. Daramola, “Experimental analysis of hyperparameters for deep learning-based churn prediction in the banking sector,” Computation, vol. 9, no. 3, 2021, Art. no. 34, doi: 10.3390/computation9030034. Crossref

Y. Yulianti and A. Saifudin, “Sequential feature selection in customer churn prediction based on naive Bayes sequential feature selection in customer churn prediction based on naive Bayes,” Institute of Physics Conf. Series: Materials Science and Engineering, vol. 879, 2020, Art. no. 012090, doi: 10.1088/1757-899X/879/1/012090. Crossref

S. Agrawal, A. Das, A. Gaikwad, and S. Dhage “Customer churn prediction modeling based on behavioural patterns analysis using deep learning,” 2018 Int. Conf. Smart Comput. Electron. Enterp., 2018, doi: 10.1109/ICSCEE.2018.8538420. Crossref

J. Pamina et al., “An effective classifier for predicting churn in telecommunication,” J. Adv. Res. in Dynamical and Control Syst., vol. 11, pp. 221–229, 2019.

E. Varun et al., “An efficient technique for feature selection to predict customer churn in telecom industry,” 2019 1st Int. Conf. Adv. Inf. Technol., 2019, pp. 174–179, doi: 10.1109/ICAIT47043.2019.8987317. Crossref

R. Bai et al., “Context aware telco churn prediction powered by temporal feature engineering,” 2018 IEEE Int. Conf. Pervasive Comput. Commun. Workshop, 2018, pp. 161–166, doi: 10.1109/PERCOMW.2018.8480416. Crossref

I. Ullah et al., “A churn prediction model using random forest: Analysis of machine learning techniques for churn prediction and factor identification in telecom sector,” IEEE Access, vol. 7, pp. 60134–60149, 2019, doi: 10.1109/ACCESS.2019.2914999. Crossref

B. N. K. Sai, and T. Sasikala, “Predictive analysis and modeling of customer churn in telecom using machine learning technique,” in Proc. 2019 3rd Int. Conf. Trends Electron. Informatics, 2019, pp. 6–11, doi: 10.1109/ICOEI.2019.8862625. Crossref

F. F. Firdaus, H. A. Nugroho, and I. Soesanti “Deep neural network with hyperparameter tuning for detection of heart disease,” 2021 IEEE Asia Pacific Conf. Wireless and Mobile, 2021, pp. 59–65, doi: 10.1109/APWiMob51111.2021.9435250. Crossref

E. Rasywir, R. Sinaga, and Y. Pratama, “Evaluasi pembangunan sistem pakar penyakit tanaman sawit dengan metode deep neural network (DNN),” J. Media Inf., vol. 4, no. 4, pp. 1206–1215, 2020, doi: 10.30865/mib.v4i4.2518. Crossref

M. R. Adi, A. B. Osmond, and A. L. Prasasti, “Penentuan dialek jawa menggunakan metode deep neural network,” eProc. Eng., vol. 6, no. 2, 2019, pp. 5637–5647.

B. W. Putra et al., “Klasifikasi arritmia pada sinyal EKG menggunakan deep neural network,” J. Penelitian Ilmu dan Teknologi Komputer, vol. 13, no. 1, pp. 29–38, 2021.

W. Treethidtaphat, W. Pattara-atikom, and S. Khaimook, “Bus arrival time prediction at any distance of bus route using deep neural network model,” 2017 IEEE 20th Int. Conf. Intell. Transp. Syst., 2017, pp. 988–992, doi: 10.1109/ITSC.2017.8317891. Crossref

M. Astiningrum, M. Mentari, and R. R. N. Rachma, “Deteksi kesegaran daging sapi berdasarkan ekstraksi fitur warna dan tekstur,” in Proc. 2019: Seminar Informatika Aplikatif, 2019, pp. 217–222.

M. Syam, J. Raharjo, and R. Patmasari, “Identifikasi asal daerah berdasarkan suara manusia dengan metode linier predictive coding (lpc),” eProc. Eng., vol. 6, no. 3, pp. 10226–10233, 2019.

H. Abhirawa, Jondri, and A. Arifianto, “Pengenalan wajah menggunakan convolutional neural network,” eProc. Eng., vol. 4, no. 3, pp. 4907–4916, 2017.

C. D. Suhendra and A. C. Saputra, “Penentuan parameter learning rate selama pembelajaran jaringan syaraf tiruan backpropagation menggunakan algoritma genetika,” J. Tek. Inform., vol. 14, no. 2, pp. 202–212, 2020, doi: 10.47111/JTI. Crossref

A. C. Sitepu and M. Sigiro, “Analisis fungsi aktivasi relu dan sigmoid menggunakan optimizer SGD dengan representasi MSE pada model backpropagation,” J. Teknik Inform. Universal, vol. 1, no. 1, pp. 12–25, 2021.

Y. Wang, J. Liu, J. Mišić, V. B. Mišić, and S. Lv, “Assessing optimizer impact on DNN model sensitivity to adversarial examples,” IEEE Access, vol. 7, pp. 152766–152776, 2019, doi: 10.1109/ACCESS.2019.2948658. Crossref

N. A. Putro, R. Septian, Widiastuti, M. Maulidah, H. F. Pardede, “Prediction of hotel booking cancellation using deep neural network and logistic regression algorithm,” Techno Nusa Mandiri: J. Comput. Inform. Technol., vol. 18, no. 1, pp. 1–8, 2020, doi: 10.33480/techno.v18i1.2056. Crossref

S. Mandt, M. D. Hoffman, and D. M. Blei, “Stochastic gradient descent as approximate Bayesian inference,” J. Machine Learning Res., vol. 18, pp. 1–35, 2017.

M. W. P. Aldi, Jondri, and A. Aditsania, “Analisis dan implementasi long short term memory neural network untuk prediksi harga bitcoin,” eProc. Eng., vol. 5, no. 2, pp. 3548–3555, 2018.

M. P. Ranjit, G. Ganapathy, K. Sridhar, and V. Arumugham “Efficient deep learning hyperparameter tuning using cloud infrastructure: Intelligent distributed hyperparameter tuning with bayesian optimization in the cloud,” 2019 IEEE 12th Int. Conf. Cloud Comput., 2019, pp. 520–522, doi: 10.1109/CLOUD.2019.00097. Crossref

S. Sautomo and H. F. Pardede, “Prediksi belanja pemerintah Indonesia menggunakan long short-term memory (LSTM),” J. Rekayasa Sist. dan Teknol. Inf., vol. 5, no. 1, pp. 99–106, 2021, doi: 10.29207/resti.v5i1.2815. Crossref


Article Metrics

Metrics Loading ...

Metrics powered by PLOS ALM

Refbacks

  • There are currently no refbacks.




Copyright (c) 2021 National Research and Innovation Agency

Creative Commons License
This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.