Evaluating Machine Learning Models Efficiency with Performance Metrics for Customer Churn Forecast in Finance Markets
DOI:
https://doi.org/10.63282/3050-9416.IJAIBDCMS-V3I1P107Keywords:
Customer Churn Prediction, Machine Learning, Random Forest, SMOTE, Financial Markets, IBM Telco DatasetAbstract
In financial markets, the competition is on the rise, and therefore, prediction of customer churn is necessary to minimize the revenue loss. Good machine learning models can tell who will be a potential churner, so these institutions can improve their retention strategies and do everything to keep customer loyalty. In financial markets, forecasting customer turnover is a significant issue because attracting prospective consumers may be more cost-effective than keeping current ones. Nevertheless, with the rise of rival financial service providers, it is crucial for institutions to have a reliable way to forecast customer turnover so they may implement proactive retention strategies and prevent significant revenue losses. This research looks at how well Multi-Layer Perceptron (MLP), Random Forest (RF), and Support Vector Machines (SVM) are three machine learning models that categorize the clients as either churners or non-churners. The mathematical framework is assessed using measurements listed below the region under the inclination (AUC ROC), F1 score, accuracy, precision, and recall. When compared to the other classifiers, RF performed the best with a 92.5% accuracy rate, 91.8% precision, 90.3% recall, 91.0% F1-score, and 0.95 AUC-ROC score. Results show that RF is an effective approach for dealing with complicated, big datasets. The study concludes that financial institutions may benefit from machine learning's enhanced prediction accuracy and its ability to assist them in identifying high-risk consumers, allowing them to implement effective customer retention tactics
References
[1] O. Adwan, H. Faris, K. Jaradat, O. Harfoushi, and N. Ghatasheh, “Predicting customer churn in telecom industry using multilayer preceptron neural networks: Modeling and analysis,” Life Sci. J., vol. 11, no. 3, pp. 75–81, 2014.
[2] V. Umayaparvathi and K. Iyakutti, “A Survey on Customer Churn Prediction in Telecom Industry: Datasets, Methods and Metrics,” Int. Res. J. Eng. Technol., 2016.
[3] C. Wang, R. Li, P. Wang, and Z. Chen, “Partition cost-sensitive CART based on customer value for Telecom customer churn prediction,” in Chinese Control Conference, CCC, 2017. doi: 10.23919/ChiCC.2017.8028259.
[4] G. Nie, W. Rowe, L. Zhang, Y. Tian, and Y. Shi, “Credit card churn forecasting by logistic regression and decision tree,” Expert Syst. Appl., 2011, doi: 10.1016/j.eswa.2011.06.028.
[5] B. Gregory, “Predicting Customer Churn: Extreme Gradient Boosting with Temporal Data First-place Entry for Customer Churn Challenge in WSDM Cup 2018,” 2018.
[6] P. Li, S. Li, T. Bi, and Y. Liu, “Telecom customer churn prediction method based on cluster stratified sampling logistic regression,” in IET Conference Publications, 2014. doi: 10.1049/cp.2014.1576.
[7] A. Idris, M. Rizwan, and A. Khan, “Churn prediction in telecom using Random Forest and PSO based data balancing in combination with various feature selection strategies,” Comput. Electr. Eng., 2012, doi: 10.1016/j.compeleceng.2012.09.001.
[8] N. Lu, H. Lin, J. Lu, and G. Zhang, “A customer churn prediction model in telecom industry using boosting,” IEEE Trans. Ind. Informatics, 2014, doi: 10.1109/TII.2012.2224355.
[9] F. Castanedo, G. Valverde, J. Zaratiegui, and A. Vazquez, “Using Deep Learning to Predict Customer Churn in a Mobile Telecommunication Network Federico,” p, 2014.
[10] W. H. Au, C. C. Chan, and X. Yao, “A novel evolutionary data mining algorithm with applications to churn prediction,” IEEE Trans. Evol. Comput., 2003, doi: 10.1109/TEVC.2003.819264.
[11] K. A. Amuda and A. B. Adeyemo, “Customers Churn Prediction in Financial Institution Using Artificial Neural Network,” 2019.
[12] R. Li, Y. Zhang, Y. Tuo, and P. Chang, “A Novel Method for Detecting Telecom Fraud User,” in Proceedings - 2018 3rd International Conference on Information Systems Engineering, ICISE 2018, 2018. doi: 10.1109/ICISE.2018.00016.
[13] A. Mishra and U. S. Reddy, “A comparative study of customer churn prediction in telecom industry using ensemble based classifiers,” in Proceedings of the International Conference on Inventive Computing and Informatics, ICICI 2017, 2018. doi: 10.1109/ICICI.2017.8365230.
[14] A. Mishra and U. S. Reddy, “A Novel Approach for Churn Prediction Using Deep Learning,” in 2017 IEEE International Conference on Computational Intelligence and Computing Research, ICCIC 2017, 2018. doi: 10.1109/ICCIC.2017.8524551.
[15] S. Agrawal, A. Das, A. Gaikwad, and S. Dhage, “Customer Churn Prediction Modelling Based on Behavioural Patterns Analysis using Deep Learning,” in 2018 International Conference on Smart Computing and Electronic Enterprise, ICSCEE 2018, 2018. doi: 10.1109/ICSCEE.2018.8538420.
[16] S. Bharadwaj, B. S. Anil, A. Pahargarh, A. Pahargarh, P. S. Gowra, and S. Kumar, “Customer Churn Prediction in Mobile Networks using Logistic Regression and Multilayer Perceptron(MLP),” in Proceedings of the 2nd International Conference on Green Computing and Internet of Things, ICGCIoT 2018, 2018. doi: 10.1109/ICGCIoT.2018.8752982.
[17] S. A. Alasadi and W. S. Bhaya, “Review of data preprocessing techniques in data mining,” J. Eng. Appl. Sci., 2017, doi: 10.3923/jeasci.2017.4102.4107.
[18] X. Tan et al., “Wireless sensor networks intrusion detection based on SMOTE and the random forest algorithm,” Sensors (Switzerland), 2019, doi: 10.3390/s19010203.
[19] J. Salminen, V. Yoganathan, J. Corporan, B. J. Jansen, and S. G. Jung, “Machine learning approach to auto-tagging online content for content marketing efficiency: A comparative analysis between methods and content type,” J. Bus. Res., 2019, doi: 10.1016/j.jbusres.2019.04.018.
[20] H. Tyralis, G. Papacharalampous, and A. Langousis, “A brief review of random forests for water scientists and practitioners and their recent history in water resources,” 2019. doi: 10.3390/w11050910.
[21] L. Gigović, H. R. Pourghasemi, S. Drobnjak, and S. Bai, “Testing a new ensemble model based on SVM and random forest in forest fire susceptibility assessment and its mapping in Serbia’s Tara National Park,” Forests, 2019, doi: 10.3390/f10050408.
[22] B. Huang, M. T. Kechadi, and B. Buckley, “Customer churn prediction in telecommunications,” Expert Syst. Appl., 2012, doi: 10.1016/j.eswa.2011.08.024.
[23] J. Burez and D. Van den Poel, “Handling class imbalance in customer churn prediction,” Expert Syst. Appl., 2009, doi: 10.1016/j.eswa.2008.05.027.
[24] [24] P. Bhanuprakash and G. S. Nagaraja, “A Review on Churn Prediction Modeling in Telecom Environment,” in 2nd International Conference on Computational Systems and Information Technology for Sustainable Solutions, CSITSS 2017, 2018. doi: 10.1109/CSITSS.2017.8447617.
[25] K. Ebrah and S. Elnasir, “Churn prediction using machine learning and recommendations plans for telecoms,” J. Comput. Commun., vol. 7, no. 11, pp. 33–53, 2019.
[26] Q. Yihui and Z. Chiyu, “Research of indicator system in customer churn prediction for telecom industry,” in ICCSE 2016 - 11th International Conference on Computer Science and Education, 2016. doi: 10.1109/ICCSE.2016.7581567.
[27] Kalla, D., Kuraku, D. S., & Samaah, F. (2021). Enhancing cyber security by predicting malwares using supervised machine learning models. International Journal of Computing and Artificial Intelligence, 2(2), 55-62.
