Prediction of Application Performance Issues Using Decision Tree Models
Keywords:
AIOps, app performance prediction, CART algorithm, decision tree, pro-active maintenance, software reliabilityAbstract
Objective: The rapid digitalization of global services has elevated software reliability to a critical component of modern infrastructure. Conventional reactive debugging approaches are increasingly inadequate, necessitating the development of proactive software quality assurance strategies. This study aimed to develop a predictive model for identifying application performance issues using system telemetry data.
Materials and Methods: A supervised machine learning approach was employed using a Decision Tree model based on the Classification and Regression Tree (CART) algorithm. The model was trained and validated on system telemetry parameters, including CPU Load, Memory Usage, Request Rate and Latency, to detect patterns associated with performance degradation.
Results: The developed model demonstrated high predictive performance, achieving 91% accuracy, 89% precision and 92% recall. Feature importance analysis indicated that Memory Usage and CPU Load were the most influential predictors of application performance issues.
Conclusion: The findings suggest that interpretable Decision Tree models, utilizing transparent “if-then” rules, can effectively transform raw system telemetry data into actionable diagnostic insights. This approach provides a scalable and practical framework for the early detection and prevention of system-wide failures, particularly in resource-constrained environments.
References
[1] C-H. Song and Y.-W. Sohn, "The influence of dependability in cloud computing adoption," J. Supercomput., vol. 78, pp. 12159-12201, 2022.
[2] “Reactive Maintenance in Software Engineering,” GeeksforGeeks. [Online]. Available: https://www.geeksforgeeks.org/software-engineering/reactive-maintenance-in-software-engineering/
[3] Gholipour, M. Zare, M. V. Sereshk and Y. Gholipour, "A comprehensive review of maintenance strategies: From reactive to proactive approaches," Cent. Asia Caucasus, vol. 26, no. 1 pp. 70-83, 2025.
[4] Hastie, R. Tibshirani and J. Friedman, The elements of statistical learning, 2nd ed. New York, NY: Springer New York, 2009, pp.745.
[5] Arifuzzaman, M. R. Hasan, T. J. Toma, S. B. Hassan and A. K. Paul, "An advanced decision tree-based deep neural network in nonlinear data classification," Technologies, vol. 11, no. 1, 2023. [Online]. Available: 10.3390/technologies11010024
[6] Kokash and L. Makhnist, "Using decision trees for interpretable supervised clustering," SN Comput. Sci., vol. 5, 2024. [Online]. Available: 10.1007/s42979-023-02590-7
[7] P. Carvalho, F. A. A. M. N. Soares, R. Vita, R. D. P. Francisco, J. P. Basto and S. G. S. Alcalá, "A systematic literature review of machine learning methods applied to predictive maintenance," Comput. s Ind. Eng., vol. 137, 2019. [Online]. Available: 10.1016/j.cie.2019.106024
[8] Kaparthi and D. Bumblauskas, "Designing predictive maintenance systems using decision tree-based machine learning techniques," Int. J. Qual. Reliab. Manage., Vol. 37, No. 4, pp. 659-686, 2020.
[9] Molnar, Interpretable Machine Learning: A Guide for Making Black Box Models Explainable, 3rd ed. Munich, Bavaria, Germany: GitHub Pages, 2025, pp. 317.
[10] Breiman, J. H. Friedman, R. A. Olshen and C. J. Stone, Classification and regression trees, 1st ed. New York, USA: Routledge, 2017, pp. 368.
[11] T. Ribeiro, S. Singh and C. Guestrin, ""Why should I trust you?": Explaining the predictions of any classifier," in Proceedings of The 22nd ACM SIGKDD International Conference On Knowledge Discovery And Data Mining, 13-17 Aug. 2016. New York, NY, USA: ACM, 2016, pp. 1135-1144.
[12] J. Murdoch, C. Singh, K. Kumbier, R. Abbasi-Asl and B. Yu, "Definitions, methods, and applications in interpretable machine learning," Proc. Natl. Acad. Sci., Vol. 116, No. 44, pp. 22071-22080, 2019.
Downloads
Published
Issue
Section
License
Copyright (c) 2026 Efren I. Balaba, Elise Jane M. Lacubtan
This work is licensed under a Creative Commons Attribution 4.0 International License.
