2692-4048ISSN (Online)
2770-0070ISSN (Print)
Volume 14 , Issue 2 , PP: 172-185, 2024 | Cite this article as | XML | Html | PDF | Full Length Article
Sergey Bakhvalov 1 , Eduard Osadchy 2 , Irina Bogdanova 3 , Rustem Shichiyakh 4 , E. Laxmi Lydia 5 *
Doi: https://doi.org/10.54216/FPA.140214
Intelligent System for Customer Churn Prediction (CCP) relates to a system or application that controls advanced artificial intelligence (AI), data analysis, and machine learning (ML) methods for anticipating and predicting customer churn in business or service. CCP approach utilizes various data sources comprising customer behavior and historical data, to create predictive method able of categorizing customers who are potential to leave or stop their engagement. By employing intelligent method, this system supports businesses in proactively addressing customer retention and executing manners to decrease churn, ultimately enhancing revenue retention and customer satisfaction. It connects wide data sources, comprising customer behavior and historical information, to progress difficult methods that can identify customers at risk of leaving or discontinuing their service or subscription. By leveraging deep learning (DL) method, this intelligent system enhances the efficiency and accuracy of customer churn prediction, allowing businesses to take proactive measures to maintain customers, maintain revenue, and develop customer satisfaction. This article presents an Intelligent System for Customer Churn Prediction using Dipper Throat Optimization with Deep Learning (ISCCP-DTODL) methodology in Telecom Industries. The purpose of the ISCCP-DTODL system focuses on the design of intelligent systems for the effective prediction of customer churners and non-churners. To accomplish this, the ISCCP-DTODL system performs Z-score data normalization to preprocess the data. For feature selection and to reduce high dimensionality of features, the ISCCP-DTODL technique uses DTO algorithm. Besides, the ISCCP-DTODL technique makes use of hybrid CNN-BiLSTM model for churn prediction. At last, jellyfish optimization (JFO) based hyperparameter tuning approach can be employed to pick hyperparameters connected to CNN-BiLSTM technique. To display enhanced performance of ISCCP-DTODL technique, a widespread set of simulations was performed. The extensive results stated that ISCCP-DTODL model illustrates improved results than its current techniques in terms of dissimilar measures.
Customer Churn Prediction , Deep Learning , Dipper Throat Optimization , Parameter tuning , Jellyfish Optimization
[1] Khattak, A., Mehak, Z., Ahmad, H., Asghar, M.U., Asghar, M.Z. and Khan, A., 2023. Customer churn prediction using composite deep learning technique. Scientific Reports, 13(1), p.17294.
[2] Dalli, A., 2022. Impact of hyperparameters on Deep Learning model for customer churn prediction in telecommunication sector. Mathematical Problems in Engineering, 2022, pp.1-11.
[3] Mena, G., Coussement, K., De Bock, K.W., De Caigny, A. and Lessmann, S., 2023. Exploiting time-varying RFM measures for customer churn prediction with deep neural networks. Annals of Operations Research, pp.1-23.
[4] Pondel, M., Wuczynski, M., Gryncewicz, W., Lysik, L., Hernes, M., Rot, A. and Kozina, A., 2021, July. Deep Learning for Customer Churn Prediction in E-Commerce Decision Support. In BIS (pp. 3-12).
[5] Abdulsalam, S.O., Ajao, J.F., Balogun, B.F. and Arowolo, M.O., 2022. A Churn Prediction System for Telecommunication Company Using Random Forest and Convolution Neural Network Algorithms. EAI Endorsed Transactions on Mobile Communications and Applications, 7(21).
[6] Equihua, J.P., Nordmark, H., Ali, M. and Lausen, B., 2023. Modelling customer churn for the retail industry in a deep learning based sequential framework. arXiv preprint arXiv:2304.00575.
[7] Jain, H., Khunteta, A. and Srivastava, S., 2022. Telecom churn prediction using CNN with variational autoencoder. In Smart Systems: Innovations in Computing: Proceedings of SSIC 2021 (pp. 583-600). Springer Singapore.
[8] Liu, D., Zhang, X., Shi, Y. and Li, H., 2021, August. Prediction of Railway Freight Customer Churn Based on Deep Forest. In International Conference on Intelligent Computing (pp. 479-489). Cham: Springer International Publishing.
[9] Ramadhanti, D., Larasati, A., Muid, A. and Mohamad, E., 2023, February. Building customer churn prediction models in Indonesian telecommunication company using decision tree algorithm. In AIP Conference Proceedings (Vol. 2654, No. 1). AIP Publishing.
[10] Shen, T.J. and Shibghatullah, A.S.B., 2022. Developing Machine Learning and Deep Learning Models for Customer Churn Prediction in Telecommunication Industry.
[11] Zhao, Y., Shao, Z., Zhao, W., Han, J., Zheng, Q. and Jing, R., 2023. Combining unsupervised and supervised classification for customer value discovery in the telecom industry: a deep learning approach. Computing, pp.1-23.
[12] Nalatissifa, H. and Pardede, H.F., 2021. Customer Decision Prediction Using Deep Neural Network on Telco Customer Churn Data. Jurnal Elektronika Dan Telekomunikasi, 21(2), pp.122-127.
[13] Sudharsan, R. and Ganesh, E.N., 2022. A Swish RNN based customer churn prediction for the telecom industry with a novel feature selection strategy. Connection Science, 34(1), pp.1855-1876.
[14] Xu, J., Liu, J., Yao, T. and Li, Y., 2023. Prediction and Big Data Impact Analysis of Telecom Churn by Backpropagation Neural Network Algorithm from the Perspective of Business Model. Big Data.
[15] Chinnaraj, R., 2022. Bio-Inspired Approach to Extend Customer Churn Prediction for the Telecom Industry in Efficient Way.
[16] Pustokhina, I.V., Pustokhin, D.A., Nguyen, P.T., Elhoseny, M. and Shankar, K., 2021. Multi-objective rain optimization algorithm with WELM model for customer churn prediction in telecommunication sector. Complex & Intelligent Systems, pp.1-13.
[17] Aghakhani Bezdi Langari, A. and Hasani, A., 2023. Customer Churn Analysis Based on The Datamining Approach: Hybrid Algorithm Incorporates Decision Tree and Bayesian Network. New Marketing Research Journal.
[18] Liu, Y., Shengdong, M., Jijian, G. and Nedjah, N., 2022. Intelligent prediction of customer churn with a fused attentional deep learning model. Mathematics, 10(24), p.4733.
[19] Sinsomboonthong, S., 2021. Efficiency comparison in prediction of normalization with data mining classification. diabetes, 768(537), p.231.
[20] Alharbi, A.H., Abdelhamid, A.A., Ibrahim, A., Towfek, S.K., Khodadadi, N., Abualigah, L., Khafaga, D.S. and Ahmed, A.E., 2023. Improved Dipper-Throated Optimization for Forecasting Metamaterial Design Bandwidth for Engineering Applications. Biomimetics, 8(2), p.241.
[21] Méndez, M., Merayo, M.G. and Núñez, M., 2023. Long-term traffic flow forecasting using a hybrid CNN-BiLSTM model. Engineering Applications of Artificial Intelligence, 121, p.106041.
[22] Ahmed Ali Agoub, R., Hançerlioğullari, A., Rahebi, J. and Lopez-Guede, J.M., 2023. Battery Charge Control in Solar Photovoltaic Systems Based on Fuzzy Logic and Jellyfish Optimization Algorithm. Applied Sciences, 13(20), p.11409.
[23] Brandusoiu, G. Toderean, H. Beleiu, Methods for churn prediction in the pre-paid mobile telecommunications industry, in 2016 International Conference on Communications (COMM), (2016), 97–100. https://doi.org/10.1109/ICComm.2016.7528311.
[24] Abdullaev, I., Prodanova, N., Ahmed, M.A., Lydia, E.L., Shrestha, B., Joshi, G.P. and Cho, W., 2023. Leveraging metaheuristics with artificial intelligence for customer churn prediction in telecom industries. Electronic Research Archive, 31(8), pp.4443-4458.
