1. SISN
  2. All Volumes and Issues
  3. Volume 17, 2025
  4. Structure of the Information System for Predicting and Interpreting Changes in the State of the Service User

Structure of the Information System for Predicting and Interpreting Changes in the State of the Service User

SISN.
2025;
Volume 17
: pp. 226 - 238
https://doi.org/10.23939/sisn2025.17.226
Authors:
  1. Maksym Klishch
  2. Halyna Lypak
  3. Nataliia Kunanets
  4. Sergiy Pasichnyk
  5. Taras Lypak
1
ernopil Ivan Pulyj national technical university, department of computer sciences, Ternopil, Ukraine
2
Ternopil Ivan Pulyj national technical university, department of computer sciences, Ternopil, Ukraine
3
Lviv Politechnik National University, Department of Information Systems and Networks
4
Lviv Polytechnic National University, department of information systems and networks, Lviv, Ukraine
5
Ternopil Ivan Pulyj national technical university, department of computer sciences, Ternopil, Ukraine

The paper investigates the problem of predicting changes in user states (including churn) based on session data using deep neural networks. The paper considers the use of long short-term memory models and convolutional neural networks, as well as the use of byte pair coding for data pre-processing. The functionality of the developed information system for forecasting changes in the state of users and interpreting forecasting models, which combines methods of data analysis, building forecasting models and explaining the results, is analysed. Experimental results have shown that byte pair encoding improves the accuracy of predictions, especially in the case of long short-term memory. This article discusses an approach to the development of an information system based on machine learning methods aimed at predicting changes in user states. The main methods and algorithms that can be used to build predictive models are analysed, including logistic regression, naive Bayesian classifier, decision tree, extreme gradient boosting, survival analysis methods and deep learning models. The effectiveness of the proposed approach is also evaluated and possible directions for further research are presented.

churn prediction
deep learning
long short-term memory
convolutional neural networks
byte pair encoding
behavioural analysis
  1. Balakrishnan N., Nair U., Sankaran P. G. Reliability Modelling and Analysis in Discrete Time. Elsevier Science & Technology Books, 2018. 508 p. DOI: http://dx.doi.org/10.1016/B978-0-12-801913-9.00001-4
  2. Bhattacharjee, S., Thukral, U., & Patil, N. (2023, December). Early Churn Prediction from Large Scale User- Product Interaction Time Series. In 2023 International Conference on Machine Learning and Applications (ICMLA) (pp. 2079-2086). IEEE. . DOI: http:// 10.1109/ICMLA58977.2023.00314
  3. Clark, T. G., Bradburn, M. J., Love, S. B., & Altman, D. G. (2003). Survival analysis part I: basic concepts and first analyses. British journal of cancer, 89(2), 232–238. DOI: https://doi.org/10.1038/sj.bjc.6601118
  4. Cox, D. R. (1972). Regression models and life                   ‐Jotaubrlneas.l of the Royal Statistical Society: Series B(Methodological), 34(2), 187-202.
  5. Customer Conversion Dataset for stuffmart.com. Kaggle. URL: https://www.kaggle.com/datasets/ muhammadshahidazeem/customer-conversion-dataset-for-stuffmart-com
  6. Gregory, B. (2018). Predicting customer churn: Extreme gradient boosting with temporal data. arXiv preprint arXiv:1802.03396.
  7. Hochreiter, S., & Schmidhuber, J. (1997). Long short-term memory. Neural computation, 9(8), 1735-1780.
  8. Kaplan E. L., Meier P. (1958). Nonparametric estimation from incomplete observations. J. Amer. Statist. Assoc. 53 (282): 457–481. doi:10.2307/2281868
  9. Khodadadi, A., Hosseini, S. A., Pajouheshgar, E., Mansouri, F., & Rabiee, H. R. (2020). ChOracle: A unified statistical framework for churn prediction. IEEE Transactions on Knowledge and Data Engineering, 34(4), 1656- 1666. DOI: https://doi.org/ 10.1109/TKDE.2020.3000456
  10. Kim, S., Shin, K. S., & Park, K. (2005). An application of support vector machines for customer churn analysis: Credit card case. Lecture Notes in Computer Science, 3611(PART II), 636-647. https://doi.org/10. 1007/11539117_91
  11. Liu, X., Xia, G., Zhang, X., Ma, W., & Yu, C. (2024). Customer churn prediction model based on hybrid neural networks. Scientific Reports, 14(1), 30707. DOI: https://doi.org/10.1038/s41598-024-79603-9
  12. Lundberg, S. M., & Lee, S. I. (2017). A unified approach to interpreting model predictions. Advances in neural information processing systems, 30. DOI: https://doi.org/ 10.48550/arXiv.1705.07874
  13. Maan, J., & Maan, H. (2023). Customer churn prediction model using explainable machine learning. arXiv preprint arXiv:2303.00960.     DOI:https://doi.org/10.48550/arXiv.2303.00960
  14. Mena, C. G., De Caigny, A., Coussement, K., De Bock, K. W., & Lessmann, S. (2019). Churn prediction with sequential data and deep neural networks. a co mparative analysis. arXiv preprint arXiv:1909.11114. https://doi.org/10.48550/arXiv.1909.11114
  15. Merchie, F., & Ernst, D. (2022). Churn prediction in online gambling. arXiv preprint arXiv:2201.02463. https://doi.org/10.48550/arXiv.2201.02463
  16. Rudd, D. H., Huo, H., & Xu, G. (2021, December). Causal analysis of customer churn using deep learning. In 2021 International  Conference  on  Digital  Society  and  Intelligent  Systems  (DSInS)  (pp.  319-324).  IEEE.  DOI:://doi.org/10.1109/DSInS54396.2021.9670561
  17. Sennrich, R., Haddow, B., & Birch, A. (2015). Neural machine translation of rare words with subword units. arXiv preprint arXiv:1508.07909.
  18. Telco Customer and Churn. Kaggle. URL: https://www.kaggle.com/datasets/blastchar/telco-customer-churn
  19. Vafeiadis, T., Diamantaras, K. I., Sarigiannidis, G., & Chatzisavvas, K. C. (2015). A comparison of machine learning techniques for customer churn prediction. Simulation Modelling Practice and Theory, 55, 1-9.
  20. Wang, D. Y. C., Jordanger, L. A., & Lin, J. C. W. (2024). Explainability of highly associated fuzzy churn patterns in binary classification. arXiv preprint arXiv:2410.15827. DOI: //https://doi.org/10.48550/arXiv.2410.15827
  21. WSDM - KKBox's Churn Prediction Challenge. (2017). Kaggle. URL: https://www.kaggle.com/competitions/kkbox-churn-prediction-challenge.
  22. Zhovnir Y., Kunanets N., Burov Y., Duda O., Pasichnyk V. (2025) Development of the structure and architecture of situational awareness security information systems for residential complexes Eastern-European Journal of Enterprise Technologies, 1(133), 8-22 DOI: https://doi.org/10.15587/1729-4061.2025.315248