International Journal of Engineering and Manufacturing (IJEM)
IJEM Vol. 16, No. 3, 8 Jun. 2026
Cover page and Table of Contents: PDF (size: 1465KB)
Feature Selection Methods for Intelligent Software Performance Monitoring Based on Machine Learning
PDF (1465KB), PP.218-237
Views: 0 Downloads: 0
Author(s)
Index Terms
Feature Selection Methods, Machine Learning, Web Applications, Telemetry Data, Adaptive Models, Cloud Systems, Microservices, Intelligent Software Monitoring
Abstract
This paper presents a set of feature selection methods for intelligent software performance monitoring based on machine learning models, with a focus on improving interpretability, scalability, and adaptability in high-dimensional telemetry analysis. The research addresses limitations of traditional statistical and rule-based approaches, which are often unable to capture nonlinear dependencies and dynamic interactions in modern distributed architectures. A unified methodology is proposed that integrates several complementary techniques for adaptive feature selection in intelligent monitoring systems. These include a topology-aware method based on graph neural networks for modeling structural dependencies in microservice architectures, a correlation-driven approach for reducing feature redundancy, a multifactor fusion method combining statistical significance, temporal stability, and predictive contribution, a cost-efficient strategy for serverless environments, and a context-aware reinforcement learning approach for dynamic feature adaptation. The proposed methods are evaluated on a large-scale dataset exceeding 3.5 TB, collected from 42 real-world applications representing monolithic, microservice, cloud-native, and serverless architectures. The results show an average reduction in feature dimensionality of 37%, while maintaining over 95% predictive accuracy across multiple models. Additional improvements include, on average, a 21% increase in dependency modeling accuracy, an 18% gain in feature relevance estimation, a 26% reduction in feature instability under dynamic workloads, and up to 42% cost reduction in serverless environments, as observed across repeated experiments under controlled workload variability and consistent evaluation settings. While the results demonstrate the effectiveness of adaptive feature selection, further validation in diverse real-world conditions is required to confirm the generalizability of the proposed framework.
Cite This Paper
Liubov Oleshchenko, Zhengbing Hu, Andrii Dychka, "Feature Selection Methods for Intelligent Software Performance Monitoring Based on Machine Learning", International Journal of Engineering and Manufacturing (IJEM), Vol.16, No.3, pp.218-237, 2026. DOI:10.5815/ijem.2026.03.13
Reference
[1]Ghattas, M., Mora, A. M., & Odeh, S. (2025). A novel approach for evaluating web page performance based on machine learning algorithms and optimization algorithms. AI, 6(2). DOI: 10.3390/ai6020019
[2]Barbieri, M. C., Grisci, B. I., & Dorn, M. (2024). Analysis and comparison of feature selection methods towards performance and stability. Expert Systems with Applications, 249. DOI: 10.1016/j.eswa.2024.123667
[3]Epstein, E., Nallapareddy, N., & Ray, S. (2023). On the relationship between feature selection metrics and accuracy. Entropy, 25(12). DOI: 10.3390/e25121646
[4]Mostert, W., Malan, K. M., & Engelbrecht, A. P. (2021). A feature selection algorithm performance metric for comparative analysis. Algorithms, 14(3). DOI: 10.3390/a14030100
[5]Muthukrishnan, R., & Rohini, R. (2016). LASSO: A feature selection technique in predictive modeling for machine learning. Proceedings of ICACA. DOI: 10.1109/ICACA.2016.7887916
[6]Pawening, R., et al. (2016). Feature selection methods based on mutual information for classifying heterogeneous features. Jurnal Ilmu Komputer dan Informasi, 9(2). DOI: 10.21609/jiki.v9i2.384
[7]Onakpojeruo, E. P., & Sancar, N. (2024). A two-stage feature selection approach based on artificial bee colony and adaptive LASSO. Applied Mathematics, 4(4). DOI: 10.3390/appliedmath4040081
[8]Li, B., et al. (2021). Enjoy your observability: An industrial survey of microservice tracing and analysis. Empirical Software Engineering, 27(1). DOI: 10.1007/s10664-021-10063-9
[9]Colarusso, C., et al. (2024). A distributed tracing pipeline for improving locality awareness of microservices applications. Software: Practice and Experience, 54(6). DOI: 10.1002/spe.3317
[10]Panahandeh, M., et al. (2024). ServiceAnomaly: Anomaly detection in microservices using traces and profiling metrics. Journal of Systems and Software, 209. DOI: 10.1016/j.jss.2023.111917
[11]Zhu, Y., et al. (2024). MicroIRC: Root cause localization for microservice systems. Journal of Systems and Software, 216. DOI: 10.1016/j.jss.2024.112145
[12]Khemani, B., et al. (2024). A review of graph neural networks: Concepts, architectures, techniques, challenges, datasets, applications, and future directions. Journal of Big Data, 11. DOI: 10.1186/s40537-023-00876-4
[13]Dai, E., et al. (2024). A comprehensive survey on trustworthy graph neural networks. Machine Intelligence Research, 21(4). DOI: 10.1007/s11633-024-1510-8
[14]Van Riet, J., Malavolta, I., & Ghaleb, T. (2023). Optimize along the way: An industrial case study on web performance. Journal of Systems and Software, 198. DOI: 10.1016/j.jss.2022.111593
[15]Gomes, F., Rego, P., & Trinta, F. (2025). A systematic mapping study on observability of microservices-based applications: fundamentals, classifications, and challenges. Computing. DOI: 10.1007/s00607-025-01540-w
[16]Hammad, Y., Ahmad, A. A.-S., & Andras, P. (2025). An empirical study on the performance overhead of code instrumentation in containerised microservices. Journal of Systems and Software. DOI: 10.1016/j.jss.2025.112573