Application of FinOps-Based Cloud Cost Risk Analysis on Microsoft Azure Services
Article Sidebar
Published:
Dec 18, 2025
Keywords:
Azure; Cloud computing; FinOps; Z-Score
Main Article Content
Abstract
The increasing adoption of cloud computing simplifies IT infrastructure management but also introduces challenges related to unpredictable cost fluctuations. This study applies a descriptive quantitative approach using the Z-Score method to detect cloud cost anomalies as an initial step in FinOps practices. Microsoft Azure service cost data from the 2023–2024 period were analyzed through data cleansing, statistical calculations, and cost trend visualization. Using a Z-Score threshold of ≥ 1.7, the results indicate that one month was identified as High Risk with a Z-Score value of 2.275, representing a significant cost spike. These findings demonstrate that the Z-Score method is capable of detecting cost deviations quickly and efficiently without requiring complex analytical models, making it effective as an early warning system prior to the adoption of more advanced analytics techniques.
Article Details
Section
Articles
References
Aljanabi, M., Abd-alwahab, S. N., Rohmat, R. D., & Raad, H. (2021). Cloud Computing Issues , Challenges , and Needs : A Survey. 5(September), 298–305.
Bhardwaj, P. (2021). Optimizing FinOps Practices with Azure Cost Management and Billing Tools. 9(3), 1–8.
Boniol, P., Liu, Q., Huang, M., Palpanas, T., & Paparrizos, J. (2024). Dive into Time-Series Anomaly Detection: A Decade Review. Proceedings of Make Sure to Enter the Correct Conference Title from Your Rights Confirmation Emai (Conference Acronym ’XX), 1(1).
Islam, M. S., Rakha, M. S., Pourmajidi, W., & Sivaloganathan, J. (2020). Anomaly Detection in Large-Scale Cloud Systems : An Industry Case and Dataset. 1–12.
Katsarou, K. (2020). A Systematic Review on Anomaly Detection for Cloud Computing Environments. 83–96. https://doi.org/10.1145/3442536.3442550
Mitropoulou, K., Kokkinos, P., Soumplis, P., & Varvarigos, E. (2024). Anomaly Detection in Cloud Computing using Knowledge Graph Embedding and Machine Learning Mechanisms. https://doi.org/10.1007/s10723-023-09727-1
Nanekalva, B. (2025). A Comparative Analysis of Statistical Anomaly Detection Methods for Cloud Service Monitoring : A Simulation-Based Evaluation Framework Methods for Cloud Service Monitoring : A Simulation-Based. 0–7.
Olausson, K. (2024). A Study on Isolation Forest for Anomaly Detection in Cloud-Based Systems.
Sikha, V. K., & Siramgari, D. (2023). Finops Practice Accelerating Innovation on Public. March, 552–562.
Wang, H., Guo, J., Ma, X., Fu, S., Yang, Q., & Xu, Y. (2021). Online Self-Evolving Anomaly Detection in Cloud Computing Environments. 1–10.
Yakkanti, P. R. (2025). AI-Enabled FinOps for Cloud Cost Optimization : Enhancing Financial Governance in Cloud Environments. 13(11), 17–29.
Article Sidebar
Main Article Content
Abstract
The increasing adoption of cloud computing simplifies IT infrastructure management but also introduces challenges related to unpredictable cost fluctuations. This study applies a descriptive quantitative approach using the Z-Score method to detect cloud cost anomalies as an initial step in FinOps practices. Microsoft Azure service cost data from the 2023–2024 period were analyzed through data cleansing, statistical calculations, and cost trend visualization. Using a Z-Score threshold of ≥ 1.7, the results indicate that one month was identified as High Risk with a Z-Score value of 2.275, representing a significant cost spike. These findings demonstrate that the Z-Score method is capable of detecting cost deviations quickly and efficiently without requiring complex analytical models, making it effective as an early warning system prior to the adoption of more advanced analytics techniques.
Article Details
References
Aljanabi, M., Abd-alwahab, S. N., Rohmat, R. D., & Raad, H. (2021). Cloud Computing Issues , Challenges , and Needs : A Survey. 5(September), 298–305.
Bhardwaj, P. (2021). Optimizing FinOps Practices with Azure Cost Management and Billing Tools. 9(3), 1–8.
Boniol, P., Liu, Q., Huang, M., Palpanas, T., & Paparrizos, J. (2024). Dive into Time-Series Anomaly Detection: A Decade Review. Proceedings of Make Sure to Enter the Correct Conference Title from Your Rights Confirmation Emai (Conference Acronym ’XX), 1(1).
Islam, M. S., Rakha, M. S., Pourmajidi, W., & Sivaloganathan, J. (2020). Anomaly Detection in Large-Scale Cloud Systems : An Industry Case and Dataset. 1–12.
Katsarou, K. (2020). A Systematic Review on Anomaly Detection for Cloud Computing Environments. 83–96. https://doi.org/10.1145/3442536.3442550
Mitropoulou, K., Kokkinos, P., Soumplis, P., & Varvarigos, E. (2024). Anomaly Detection in Cloud Computing using Knowledge Graph Embedding and Machine Learning Mechanisms. https://doi.org/10.1007/s10723-023-09727-1
Nanekalva, B. (2025). A Comparative Analysis of Statistical Anomaly Detection Methods for Cloud Service Monitoring : A Simulation-Based Evaluation Framework Methods for Cloud Service Monitoring : A Simulation-Based. 0–7.
Olausson, K. (2024). A Study on Isolation Forest for Anomaly Detection in Cloud-Based Systems.
Sikha, V. K., & Siramgari, D. (2023). Finops Practice Accelerating Innovation on Public. March, 552–562.
Wang, H., Guo, J., Ma, X., Fu, S., Yang, Q., & Xu, Y. (2021). Online Self-Evolving Anomaly Detection in Cloud Computing Environments. 1–10.
Yakkanti, P. R. (2025). AI-Enabled FinOps for Cloud Cost Optimization : Enhancing Financial Governance in Cloud Environments. 13(11), 17–29.