Keywords
eXplainable artificial intelligence (XAI)
LIME
SHAP (SHapley Additive exPlanations)
How to Cite
Abstract
In many industries, such as the telecommunications industry, identifying the causes of customer churn is a primary challenge. In the telecommunications industry, it is of great importance to predict which customers will abandon or continue their subscriptions. Machine learning and data science offer numerous solutions to this problem. These proposed solutions have an important place in decision making processes in various sectors. This study aims to predict lost customers using machine learning algorithms and explain the reasons behind them. The dataset used used Linear Regression, Logistic Regression, Naive Bayes, Decision Tree, Random Forest, K-Nearest Neighbors (KNN), Gradient Boosting, XGBoost (eXtreme Gradient Boosting), LightGBM, AdaBoost and CatBoost to find the classification with the best performance. Contains algorithms. model. Performance metrics such as R2 score, Mean Square Error, Mean Absolute Error, Root Mean Square Error and Accuracy are used in this process. Finally, the LightGBMmodel, which gives the highest accuracy value (73.085%), is explained using explainable artificial intelligence (XAI) algorithms.
References
Alawin, A. and M. Al-ma’aitah, 2014 Proposed ranking for point of sales using data mining for telecom operators. IJDMS 6: 17–31.
Ali, S. et al., 2023 Explainable artificial intelligence (xai): What we know and what is left to attain trustworthy artificial intelligence. Information Fusion 99: 101805.
Almrshed, S. K. H., H. M. Jasim, and A. S. Hassan, 2023 The effect of innovation management on sustainable competitive advantage in contemporary organizations. Journal of Law and Sustainable Development 11: e1980–e1980.
Amin, A., 2024 Cell2cell duke university telco dataset. Accessed: Aug. 20, 2024. [Online]. Available: https://www.kaggle.com/datasets/geoamins/cell2cellduke-university-telco-dataset.
Bhattacharyya, J. and M. K. Dash, 2022 What do we know about customer churn behaviour in the telecommunication industry? a bibliometric analysis of research trends, 1985–2019. FIIB Business Review 11: 280–302.
Cambra-Fierro, J. J., I. Melero-Polo, and R. Vázquez-Carrasco, 2013 Customer engagement: Innovation in non-technical marketing processes. Innovation 15: 326–336.
Chouiekh, A. and E. H. I. E. Haj, 2017 Machine learning techniques applied to prepaid subscribers: Case study on the telecom industry of morocco. In 2017 Intelligent Systems and Computer Vision (ISCV), pp. 1–8.
Feng, D.-C., W.-J. Wang, S. Mangalathu, and E. Taciroglu, 2021 Interpretable xgboost-shap machine-learning model for shear strength prediction of squat rc walls. Journal of Structural Engineering 147: 04021173.
Franchini, S. and R. Balzan, 2023 Large-deviation theory of increasing returns. Phys. Rev. E 107: 064142.
Garreau, D. and U. von Luxburg, 2020 Explaining the explainer: A first theoretical analysis of lime. arXiv:2001.03447.
Gaurav, D. and S. Tiwari, 2023 Interpretability vs explainability: The black box of machine learning. In 2023 International Conference on Computer Science, Information Technology and Engineering (ICCoSITE), pp. 523–528.
Gunning, D., M. Stefik, J. Choi, T. Miller, S. Stumpf, et al., 2019 Xai—explainable artificial intelligence. Science Robotics 4: eaay7120.
Gülkesen, K. H., ˙Is. T. Köksal, S. Özdem, and O. Saka, 2010 Prediction of prostate cancer using decision tree algorithm. Turkish Journal of Medical Sciences.
Harahap, M. A. K., A. M. A. Ausat, and S. Suherlan, 2023 Analysing the role of religious education in improving the work ethic of msme owners. Journal on Education 5: Art. no. 4.
Hmoud, H., F. Shishan, Z. Qasem, and S. Bazi, 2023 The effect of arabic language type on banking chatbots adoption. Heliyon 9: e20686.
Huang, Y., B. Q. Huang, and M. T. Kechadi, 2010 A new filter feature selection approach for customer churn prediction in telecommunications. In 2010 IEEE International Conference on Industrial Engineering and Engineering Management, pp. 338–342.
Idris, A., M. Rizwan, and A. Khan, 2012 Churn prediction in telecom using random forest and pso based data balancing in combination with various feature selection strategies. Computers & Electrical Engineering 38: 1808–1819.
Knapic, S., A. Malhi, R. Saluja, and K. Främling, 2021 Explainable artificial intelligence for human decision support system in the medical domain. Machine Learning and Knowledge Extraction 3: Art. no. 3.
Korkmaz, M. and K. Kaplan, 2023 ¸Seker hastalı ˘ gı te¸shisi ve önerilen modellerinin kar¸sıla¸stırılması. NÖHÜ Müh. Bilim. Derg. 12: Art. no. 1.
Kul, S. and A. Sayar, 2021 Yapay sinir a˘ gları, destek vektör makineleri ve adaboost algoritması ile araç sınıflandırmasının de˘ gerlendirilmesi. EJOSAT p. Art. no. 29.
Kılınç, D., E. Boranda˘ g, F. Yücalar, V. Tunalı, M. ¸Sim¸sek, et al., 2016 Knn algoritması ve r dili ile metin madencili˘ gi kullanılarak bilimsel makale tasnifi. MFBD 28: Art. no. 3.
Mohammed, R., E. A. Elmajid, H. Amine, and C. Khadija, 2023 Acceptance factors of telemedicine technology during covid-19 pandemic among health professionals: A qualitative study. Healthcare Technology Letters 10: 23–33.
Nahzat, S. and M. Ya˘gano˘ glu, 2021 Diabetes prediction using machine learning classification algorithms. EJOSAT p. Art. no. 24.
Nusrat, F., B. Uzba¸s, and K. Baykan, 2020 Prediction of diabetes mellitus by using gradient boosting classification. EJOSAT pp. 268–272.
Ogungbire, A. and S. S. Pulugurtha, 2023 Does non-motorists’ safety perception of autonomous vehicles vary across opinion change stemming from crash occurrence? investigating perceptions using fixed and random parameter ordered logit models. Heliyon 9: e19913.
Orulluoglu, O., 2023 Naive bayes algorithm: A simple and powerful classification method. Accessed: Aug. 20, 2024. [Online]. Available: https://medium.com/@bayramorkunor/naivebayes-algorithm-a-simple-and-powerful-classification-method-7f58a1eb975c.
Pettersson, M., 2004 Spc with applications to churn management. Quality and Reliability Engineering International 20: 397–406.
Ribeiro, H., B. Barbosa, A. C. Moreira, and R. G. Rodrigues, 2024 Determinants of churn in telecommunication services: a systematic literature review. Management Review Quarterly 74: 1327–1364.
Shen, Q., H. Li, Q. Liao, W. Zhang, and K. Kalilou, 2014 Improving churn prediction in telecommunications using complementary fusion of multilayer features based on factorization and construction. In The 26th Chinese Control and Decision Conference (2014 CCDC), pp. 2250–2255.
Speith, T., 2022 A review of taxonomies of explainable artificial intelligence (xai) methods. In Proceedings of the 2022 ACM Conference on Fairness, Accountability, and Transparency, Accessed: Aug. 20, 2024. [Online]. Available: https://dl.acm.org/doi/10.1145/3531146.3534639.
Sun, K.-A. and J. Moon, 2023 Assessing antecedents of restaurant’s brand trust and brand loyalty, and moderating role of food healthiness. Nutrients 15: Art. no. 24.
Suryawan, R. F. et al., 2023 Improving consumer loyalty by providing service excellent and utilizing business relationships. WSEAS Transactions on Business and Economics 20: 1463–1476.
Vilone, G. and L. Longo, 2021 Notions of explainability and evaluation approaches for explainable artificial intelligence. Information Fusion 76: 89–106.
Yuan, X., 2023 Telecom customer churn prediction in context of composite model. In Second International Conference on Statistics, Applied Mathematics, and Computing Science (CSAMCS 2022), pp. 690–695, SPIE.
Zhang, J. et al., 2023 Insights into geospatial heterogeneity of landslide susceptibility based on the shap-xgboost model. Journal of Environmental Management 332: 117357.
Özdemir, S., 2018 Random forest yöntemi kullanılarak potansiyel da˘gılım modellemesi ve haritalaması: Yukarıgökdere yöresi örne˘ gi. Turkish Journal of Forestry 19: Art. no. 1.
˙Ipek, A. B., 2021 Prediction of market-clearing price using neural networks based methods and boosting algorithms. International Advanced Research Engineering Journal (Int. Adv. Res. Eng. J.) 5: Art. no. 2.
Sahinaslan, , H. Dalyan, and E. ¸Sahinaslan, 2022 Naive bayes sınıflandırıcısı kullanılarak youtube verileri Üzerinden Çok dilli duygu analizi. Bili¸sim Teknolojileri Dergisi 15: Art. no. 2.
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.