ALaa KHudhair ali (1), Zeinh Sabeeh Jaseem (2), Ruaa Kadhim Jabir (3)
General Background: The growing dependence on computer systems across industrial and service sectors has increased the need for reliable early failure prediction to ensure operational continuity. Specific Background: Recent advances in artificial intelligence, particularly ensemble methods, gradient boosting algorithms, Automated Machine Learning (AutoML), and Explainable AI (XAI), have demonstrated strong potential in analyzing complex operational data for predictive maintenance. Knowledge Gap: Existing studies largely address these techniques in isolation, with limited focus on their integrated application and interpretability in real-world, dynamic environments. Aims: This review examines recent AI-based approaches for computer system failure prediction, emphasizing ensemble learning, gradient boosting, AutoML, and XAI. Results: The analysis indicates that gradient boosting and ensemble models offer superior predictive accuracy, while AutoML reduces development effort and XAI enhances model transparency and trust. Novelty: The review highlights the combined role of performance-driven and explainability-focused techniques within a unified predictive framework. Implications: Integrating these approaches supports more reliable, interpretable, and cost-effective predictive maintenance strategies in modern computing systems.Keywords : Computer System Failure Prediction, Artificial Intelligence, Ensemble Methods, Gradient Boosting, Explainable Artificial IntelligenceHighlight :
Combined model strategies consistently outperform conventional monitoring by capturing complex operational patterns.
Sequential tree-based learners demonstrate strong suitability for large-scale, noisy, and heterogeneous operational data.
Interpretation frameworks strengthen practitioner trust by clarifying decision rationales for preventive maintenance actions
L. Breiman, "Random Forests," Machine Learning, vol. 45, no. 1, pp. 5-32, Oct. 2001, doi: 10.1023/A:1010933404324.
T. Chen and C. Guestrin, "XGBoost: A Scalable Tree Boosting System," in Proc. 22nd ACM SIGKDD Int. Conf. Knowledge Discovery and Data Mining, San Francisco, CA, USA, Aug. 2016, pp. 785-794, doi: 10.1145/2939672.2939785.
J. H. Friedman, "Greedy Function Approximation: A Gradient Boosting Machine," The Annals of Statistics, vol. 29, no. 5, pp. 1189-1232, Oct. 2001, doi: 10.1214/aos/1013203451.
F. Hutter, L. Kotthoff, and J. Vanschoren, Eds., Automated Machine Learning: Methods, Systems, Challenges. Cham, Switzerland: Springer, 2019, doi: 10.1007/978-3-030-05318-5.
S. M. Lundberg and S.-I. Lee, "A Unified Approach to Interpreting Model Predictions," in Advances in Neural Information Processing Systems 30 (NIPS 2017), Long Beach, CA, USA, Dec. 2017, pp. 4765-4774.
C. Molnar, Interpretable Machine Learning: A Guide for Making Black Box Models Explainable, 2nd ed. Munich, Germany: Self-published, 2022. Available: https://christophm.github.io/interpretable-ml-book/
L. Prokhorenkova, G. Gusev, A. Vorobev, A. V. Dorogush, and A. Gulin, "CatBoost: Unbiased Boosting with Categorical Features," in Advances in Neural Information Processing Systems 31 (NeurIPS 2018), Montreal, QC, Canada, Dec. 2018, pp. 6638-6648.
M. T. Ribeiro, S. Singh, and C. Guestrin, "'Why Should I Trust You?' Explaining the Predictions of Any Classifier," in Proc. 22nd ACM SIGKDD Int. Conf. Knowledge Discovery and Data Mining, San Francisco, CA, USA, Aug. 2016, pp. 1135-1144, doi: 10.1145/2939672.2939778.
V. Shaposhnikova, "Explainable AI for Predictive Maintenance: A Systematic Literature Review," Journal of Intelligent Manufacturing, vol. 31, no. 5, pp. 1149-1161, Jun. 2020, doi: 10.1007/s10845-019-01536-8.
F. Tan, X. Li, and H. He, "Failure Prediction in Cloud Computing Systems Using Deep Learning," IEEE Transactions on Cloud Computing, vol. 6, no. 2, pp. 442-454, Apr.-Jun. 2018, doi: 10.1109/TCC.2015.2511767.
C. Thornton, F. Hutter, H. H. Hoos, and K. Leyton-Brown, "Auto-WEKA: Combined Selection and Hyperparameter Optimization of Classification Algorithms," in Proc. 19th ACM SIGKDD Int. Conf. Knowledge Discovery and Data Mining, Chicago, IL, USA, Aug. 2013, pp. 847-855, doi: 10.1145/2487575.2487629.
Y. Zhang, "Machine Learning-Based Failure Prediction in Computing Systems: A Survey," IEEE Transactions on Services Computing, vol. 14, no. 6, pp. 1580-1595, Nov.-Dec. 2021, doi: 10.1109/TSC.2019.2892396.
L. Breiman, "Bagging Predictors," Machine Learning, vol. 24, no. 2, pp. 123-140, Aug. 1996, doi: 10.1023/A:1018054314350.
A. Geron, Hands-On Machine Learning with Scikit-Learn, Keras, and TensorFlow: Concepts, Tools, and Techniques to Build Intelligent Systems, 2nd ed. Sebastopol, CA, USA: O'Reilly Media, 2019.
B. Zadrozny and C. Elkan, "Transforming Classifier Scores into Accurate Multiclass Probability Estimates," in Proc. 8th ACM SIGKDD Int. Conf. Knowledge Discovery and Data Mining, Edmonton, AB, Canada, Jul. 2002, pp. 694-699, doi: 10.1145/775047.775151.