# Understanding Practitioners Perspectives on Monitoring Machine Learning Systems

arXiv: https://arxiv.org/abs/2509.25195 · HTML: https://mlsanity.com/paper/2509.25195/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 18 of its 53 references that are in the map.
- First posted on arXiv 20 Aug 2025.

## Builds on (most cited first, 18 of 18)

- [A Survey on LLM-as-a-Judge](https://mlsanity.com/paper/2411.15594/) (2024)
- [Machine Learning Operations (MLOps): Overview, Definition, and Architecture](https://mlsanity.com/paper/2205.02302/) (2022)
- [Beyond Functional Correctness: Exploring Hallucinations in LLM-Generated Code](https://mlsanity.com/paper/2404.00971/) (2024)
- [The social dilemma of autonomous vehicles](https://mlsanity.com/paper/1510.03346/) (2015)
- [Towards CRISP-ML(Q): A Machine Learning Process Model with Quality Assurance Methodology](https://mlsanity.com/paper/2003.05155/) (2020)
- [Generative Artificial Intelligence for Software Engineering -- A Research Agenda](https://mlsanity.com/paper/2310.18648/) (2023)
- [Characterizing and Detecting Mismatch in Machine-Learning-Enabled Systems](https://mlsanity.com/paper/2103.14101/) (2021)
- [A Human-Centric Take on Model Monitoring](https://mlsanity.com/paper/2206.02868/) (2022)
- [Requirements Practices and Gaps When Engineering Human-Centered Artificial Intelligence Systems](https://mlsanity.com/paper/2301.10404/) (2023)
- [Model-driven Engineering for Machine Learning Components: A Systematic Literature Review](https://mlsanity.com/paper/2311.00284/) (2023)
- [A monitoring framework for deployed machine learning models with supply chain examples](https://mlsanity.com/paper/2211.06239/) (2022)
- ["We Have No Idea How Models will Behave in Production until Production": How Engineers Operationalize Machine Learning](https://mlsanity.com/paper/2403.16795/) (2024)
- [An investigation of challenges encountered when specifying training data and runtime monitors for safety critical ML applications](https://mlsanity.com/paper/2301.13476/) (2023)
- [Fairness Concerns in App Reviews: A Study on AI-based Mobile Apps](https://mlsanity.com/paper/2401.08097/) (2024)
- [ML-Enabled Systems Model Deployment and Monitoring: Status Quo and Problems](https://mlsanity.com/paper/2402.05333/) (2024)
- [Insights on Microservice Architecture Through the Eyes of Industry Practitioners](https://mlsanity.com/paper/2408.10434/) (2024)
- [AI Total: Analyzing Security ML Models with Imperfect Data in Production](https://mlsanity.com/paper/2110.07028/) (2021)
- [A Developer-Centric Study Exploring Mobile Application Security Practices and Challenges](https://mlsanity.com/paper/2408.09032/) (2024)

## Abstract (arXiv)

Given the inherent non-deterministic nature of machine learning (ML) systems, their behavior in production environments can lead to unforeseen and potentially dangerous outcomes. For a timely detection of unwanted behavior and to prevent organizations from financial and reputational damage, monitoring these systems is essential. This paper explores the strategies, challenges, and improvement opportunities for monitoring ML systems from the practitioners perspective. We conducted a global survey of 91 ML practitioners to collect diverse insights into current monitoring practices for ML systems. We aim to complement existing research through our qualitative and quantitative analyses, focusing on prevalent runtime issues, industrial monitoring and mitigation practices, key challenges, and desired enhancements in future monitoring tools. Our findings reveal that practitioners frequently struggle with runtime issues related to declining model performance, exceeding latency, and security violations. While most prefer automated monitoring for its increased efficiency, many still rely on manual approaches due to the complexity or lack of appropriate automation solutions. Practitioners report that the initial setup and configuration of monitoring tools is often complicated and challenging, particularly when integrating with ML systems and setting alert thresholds. Moreover, practitioners find that monitoring adds extra workload, strains resources, and causes alert fatigue. The desired improvements from the practitioners perspective are: automated generation and deployment of monitors, improved support for performance and fairness monitoring, and recommendations for resolving runtime issues. These insights offer valuable guidance for the future development of ML monitoring tools that are better aligned with practitioners needs.