Challenges in Deploying Machine Learning: A Survey of Case Studies
Open accessThe DOI matches its Crossref record; 127 of the 128 references it cites were found in a registry or an index.
Abstract
In recent years, machine learning has transitioned from a field of academic research interest to a field capable of solving real-world business problems. However, the deployment of machine learning models in production systems can present a number of issues and concerns. This survey reviews published reports of deploying machine learning solutions in a variety of use cases, industries, and applications and extracts practical considerations corresponding to stages of the machine learning deployment workflow. By mapping found challenges to the steps of the machine learning deployment workflow, we show that practitioners face issues at each stage of the deployment process. The goal of this article is to lay out a research agenda to explore approaches addressing these challenges.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
The cited source says what the claim attributes to it.
In the citing paper
“Compared with the first step, continual monitoring is used to identify data distribution drift, control model quality, and trigger system alarms when an ML model deviates from its normal behavior in the target setting [15].”
From Toward real‐world deployment of machine learning for health care: External validation, continual monitoring, and randomized clinical trials (2024) · cites this paper as [15]
The check wasn’t confident either way, so it gives no verdict — never disputed.
In the citing paper
“Our literature review was conducted using a systematic mapping protocol [54] in order to select a small set of relevant articles from the much larger collection of literature emerging at the intersection of data quality and ML.”
From A Survey of Data Quality Requirements That Matter in ML Development Pipelines (2023) · cites this paper as [54]
Experimental — accuracy not yet measured
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
Devlin, J., Chang, M.-W., Lee, K., & Toutanova, K. (2019) · Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers) · doi:10.18653/v1/n19-1423 · Cited by 54,325 · cited 2×
“They took one of the state-of-the-art models in the field, BERT [47], and found out that depending on the chosen model size full training procedure can cost anywhere between $50k and $1.”
BackgroundQuinlan, J. R. (1986) · Machine Learning · doi:10.1007/bf00116251 · Cited by 21,439 · cited 1×
“For that reason decision trees (DT) [108], which can be considered a fairly basic ML algorithm, are widely used in practice.”
MethodArmstrong, J. S., & Georgoff, D. M. (1988) · International Journal of Forecasting · doi:10.1016/0169-2070(88)90019-2 · Cited by 17,894
Rudin, C. (2019) · Nature Machine Intelligence · doi:10.1038/s42256-019-0048-x · Cited by 10,561 · cited 1×
“Rudin [111] called the ML community to stop using black box models and explaining their behavior afterward, and instead design models that are inherently interpretable.”
BackgroundOn the Dangers of Stochastic Parrots: Can Language Models Be Too Big? 🦜
Bender, E. M., Gebru, T., McMillan-Major, A., & Shmitchell, S. (2021) · Proceedings of the 2021 ACM Conference on Fairness, Accountability, and Transparency · doi:10.1145/3442188.3445922 · Cited by 6,988
Fully homomorphic encryption using ideal lattices
Gentry, C. (2009) · Proceedings of the forty-first annual ACM symposium on Theory of computing · doi:10.1145/1536414.1536440 · Cited by 6,806 · cited 1×
“Some of the ways this trade-of is resolved in practice are diferential privacy that explicitly corrupts the data [42], homomorphic encryption that restricts the class of learning algorithm but allows for training on encrypted data [50], and federated learning that distributes training across personal devices to preser…”
BackgroundPractical Bayesian Optimization of Machine Learning Algorithms
Snoek, J., Larochelle, H., & Adams, R. P. (2012) · arXiv · doi:10.48550/arxiv.1206.2944 · Cited by 6,691 · cited 1×
“Even approaches like Hyperband [78] or Bayesian optimization [129], that are speciically designed to minimize the number of training cycles needed, are not yet able to deal with the high dimensional searches that emerge when many hyper-parameters are involved.”
Dwork, C. (2006) · Lecture Notes in Computer Science · doi:10.1007/11787006_1 · Cited by 5,291 · cited 1×
“Some of the ways this tradeoff is resolved in practice are differential privacy that explicitly corrupts the data [54], homomorphic encryption that restricts the class of learning algorithm but allows for training on encrypted data [55], and federated learning that distributes training across personal devices to prese…”
BackgroundMembership Inference Attacks Against Machine Learning Models
Shokri, R., Stronati, M., Song, C., & Shmatikov, V. (2017) · 2017 IEEE Symposium on Security and Privacy (SP) · doi:10.1109/sp.2017.41 · Cited by 4,754 · cited 1×
“They veriied it on models trained on leading ML-as-a-service providers [127], achieving anywhere from 70% up to 94% accuracy of membership inference.”
BackgroundA survey on concept drift adaptation
Gama, J., Žliobaitė, I., Bifet, A., Pechenizkiy, M., & Bouchachia, A. (2014) · ACM Computing Surveys · doi:10.1145/2523813 · Cited by 3,735 · cited 1×
“We refer interested readers to the works on using domain adaptation [48], meta-learning [46] and transfer learning [152, 157] as ways of addressing dataset shift.”
Method
Research works printed but not linked: 26
- Arif Cam, Michael Chui, and Bryce Hall. 2019. Global AI survey: AI proves its worth, but few scale impact. McKinsey Analytics (2019). https://www.mckinsey.com/featured-insights/artificial-intelligence/global-ai-survey-ai-proves-its-worth-but-few-scale-impact. Accessed from 13/06/2022.
- Royal Society (Great Britain). 2017. Machine Learning: The Power and Promise of Computers that Learn by Example: an Introduction. Royal Society.
- Ben Lorica and Nathan Paco. 2018. The State of Machine Learning Adoption in the Enterprise. O’Reilly Media.
- Colin Shearer. 2000. The CRISP-DM model: The new blueprint for data mining. J. Data Warehous. 5, 4 (2000), 13–22.
- Rajashree Y. Patil and R. V. Kulkarni. 2012. A review of data cleaning algorithms for data warehouse systems. Int. J. Comput. Sci. Inf. Technol. 3, 5 (2012), 5212–5214.
- 10.1109/TITS.2019.2962338 · DOI · Paper page
- Diego Charrez. 2019. NeurIPS 2019 Stats. Retrieved from https://medium.com/@dcharrezt/neurips-2019-stats-c91346d31c8f.
- 10.1023/A:1022643204877 · doi:10.1023/a:1022643204877 · Paper page
- 10.5555/3122009.3242042 · doi:10.5555/3122009.3242042
- Bobak Shahriari, Alexandre Bouchard-Cote, and Nando Freitas. 2016. Unbounded Bayesian optimization via regularization. In Proceedings of the 19th International Conference on Artificial Intelligence and Statistics (Proceedings of Machine Learning Research), Arthur Gretton and Christian C. Robert (Eds.), Vol. 51. PMLR, 1168–1176. Retrieved from http://proceedings.mlr.press/v51/shahriari16.html.
- Ram Ananth, Seph Mard, and Peter Simon. 2019. Opening the “Black Box”: The path to deployment of AI models in banking, white paper. DataRobot (2019). https://www.datarobot.com/resources/opening-the-black-box/. Accessed from 13/06/2022.
- Robert Soden Dennis Wagenaar Dave Luo and Annegien Tijssen. 2019. Taking Ethics Fairness and Bias Seriously in Machine Learning for Disaster Risk Management. arxiv:cs.CY/1912.05538.
- Nantheera Anantrasirichai and David Bull. 2021. Artificial intelligence in the creative industries: A review. Artif. Intell. Rev. (2021), 1–68.
- D. Malan et al. 2016. Values and the fourth industrial revolution: Connecting the dots between value, values, profit and purpose. In Proceedings of the World Economic Forum.
- Daniel Malan. 2018. The law can’t keep up with new tech. Here’s how to close the gap. In Proceedings of the World Economic Forum.
- Ramprakash Ramamoorthy P. Satya Madhuri and Malini Christina Raj. 2019. AI from labs to production—challenges and learnings. USENIX Association. https://www.usenix.org/conference/opml19/presentation/madhuri. Accessed from 13/06/2022.
- Oscar Schwartz. 2019. In 2016 Microsoft’s racist chatbot revealed the dangers of online conversation. IEEE Spectr. 11 (2019).
- Florian Tramèr, Fan Zhang, Ari Juels, Michael K. Reiter, and Thomas Ristenpart. 2016. Stealing machine learning models via prediction APIs. In Proceedings of the 25th USENIX Security Symposium (USENIX Security’16). 601–618.
- Jeremy Hermann and Mike Del Balso. 2017. Meet Michelangelo: Uber’s machine learning platform. Retrieved from https://eng.uber.com/michelangelo.
- Matei Zaharia, Andrew Chen, Aaron Davidson, Ali Ghodsi, Sue Ann Hong, Andy Konwinski, Siddharth Murching, Tomas Nykodym, Paul Ogilvie, Mani Parkhe, et al. 2018. Accelerating the machine learning lifecycle with MLflow.IEEE Data Eng. Bull. 41, 4 (2018), 39–45.
- Nick Hynes, D. Sculley, and Michael Terry. 2017. The Data Linter: Lightweight, automated sanity checking for ML data sets. In Proceedings of the NIPS MLSys Workshop.
- Matthias Feurer, Aaron Klein, Katharina Eggensperger, Jost Springenberg, Manuel Blum, and Frank Hutter. 2015. Efficient and robust automated machine learning. In Advances in Neural Information Processing Systems, C. Cortes, N. Lawrence, D. Lee, M. Sugiyama, and R. Garnett (Eds.), Vol. 28. Curran Associates, Inc. Retrieved from https://proceedings.neurips.cc/paper/2015/file/11d0e6287202fced83f79975ec59a3a6-Paper.pdf.
- Randal S. Olson and Jason H. Moore. 2016. TPOT: A tree-based pipeline optimization tool for automating machine learning. In Proceedings of the Workshop on Automatic Machine Learning. PMLR, 66–74.
- Stephan Rabanser, Stephan Günnemann, and Zachary Chase Lipton. 2019. Failing loudly: An empirical study of methods for detecting dataset shift. In Proceedings of the Neural Information Processing Systems Foundation Conference.
- Chelsea Finn, Pieter Abbeel, and Sergey Levine. 2017. Model-agnostic meta-learning for fast adaptation of deep networks. In Proceedings of the International Conference on Machine Learning. PMLR, 1126–1135.
- A. Zujus. 2018. AI project development–how project managers should prepare. Tratto il giorno Agosto 31 (2018), 2019.
Cited by
Items 601–700 of 737
Effectiveness of static text adversarial methods on continuously updating models
Yu, Z., Sun, J. S. J. F., Chen, Q., & Palade, V. (2026) · Neural Networks · doi:10.1016/j.neunet.2026.108959
Gumisiriza, J., Lei, M., Zhang, S., & Shaodan, Z. (2026) · SSRN Electronic Journal · doi:10.2139/ssrn.6582143
Gumisiriza, J., Lei, M., Zhang, S., & Shaodan, Z. (2026) · SSRN Electronic Journal · doi:10.2139/ssrn.6582145
Wang, H., Yang, J. Y., & Lee, Y. (2025) · International Conference on Cloud and Big Data Computing (ICCBDC) · doi:10.1109/iccbdc67784.2025.00012
Bias-Forecasting: Predicting Ethical Failures in AI Models Before Deployment
Pandruju, S. (2026) · IEEE SoutheastCon · doi:10.1109/southeastcon63549.2026.11476344
“The framework culminates in an interactive Ethical Risk Dashboard that visualizes predicted fairness violations, uncertainty estimates, and actionable mitigation recommendations, enabling proactive ethical risk management integrated into modern MLOps workflows [27].”
Muccini, H. (2026) · Lecture notes in business information processing · doi:10.1007/978-3-032-24216-7_1
Yao, X., Zhang, J., Chen, D., Wang, B., & Yuan, L. (2026) · Agronomy Journal · doi:10.1002/agj2.70398 · Cited by 1
Integrating Machine Learning for Dynamic Resource Allocation in Civil Engineering Project Scheduling
Mokoena, T., & Nkosi, S. (2025) · Civil Engineering Science and Technology · doi:10.51903/b5d4sw69
Ploskonka, M. (2026) · Acta Informatica Pragensia · doi:10.18267/j.aip.313
Soria‐Olivas, E., Belda, E. A., Salvador, D. B., Cámara, P. H., Isla, M. A. S.-M., & Belenguer, P. R. (2026) · Studies in computational intelligence · doi:10.1007/978-3-032-15854-3_9
The Six Gestalts: Reframing Hard and Soft Skills into Systemic Roles for Professional Growth
Gerbolés, C. G.-C., Costas, J., Díez, R. P., & Pastor-Climent, R. (2026) · Dirección y Organización · doi:10.37610/88.727
Integrating Jenkins with AIOps Platforms for Hybrid SAP Basis Automation: A reference architecture
Singh, A. (2026) · International Journal of Science and Research Archive · doi:10.30574/ijsra.2026.19.1.0898
An Imbalance-Aware Machine Learning Framework for Smishing Detection in SMS-Based Mobile BankingPreprint
Amoafo, K., Akrong, G. B., Aquah, E., Ansah, P. A. K., & Owusu, E. (2026) · Research Square · doi:10.21203/rs.3.rs-9604232/v1
Solar Irradiance Forecasting Approaches Based on Machine Learning: A Systematic Literature Review
Leholo, S. T., Tu, C., & Mathonsi, T. E. (2026) · International Journal of Advanced Computer Science and Applications · doi:10.14569/ijacsa.2026.0170447
“Issues with data quality, non-stationarity and distributional changes due to seasonal variability, climate anomalies, or sensor degradation can cause Model performance to degrade [8].”
Unified Black-Box Adversarial Evasion for Neural and Non-Differentiable Learners
Sharif, D. M., & Beitollahi, H. (2026) · Cybernetics & Systems · doi:10.1080/01969722.2026.2662382
AI and Machine Learning Deployment: Best Practices, Costs and Priorities
Williams, N., Cummings, J., Wang, Y., & Gokce, Y. E. (2026) · Journal of Information Systems Applied Research and Analytics · doi:10.62273/zvnr9663
Failure Modes in AI-Augmented Data Systems: A Technical Analysis
Mishra, A. (2026) · Computer Fraud & Security · doi:10.52710/cfs.1057
An integrated machine learning method for enhancing emergency response planning
Butsingkorn, T., Apichottanakul, A., & Arunyanart, S. (2026) · Decision Analytics Journal · doi:10.1016/j.dajour.2026.100714
Deep Learning Based Crack Detection MLOps Pipeline using Incremental Learning
Rai, S., Mathur, R., Saad, A., Tonse, M. T., & Zualkernan, I. A. (2026) · International Conference on Advances in Artificial Intelligence and Machine Learning (AAIML) · doi:10.1109/aaiml67890.2026.11498221
“The gap between research and production deployment is widely recognized [16].”
Amrapali Chavan, A. P., & Patil, A. P. V. (2026) · International Journal of Advanced Research in Science Communication and Technology · doi:10.48175/ijarsct-34635
An ontology-guided knowledge model for requirements engineering of trustworthy AI systems
Sadovski, E., Aviv, I., & Hadar, I. (2026) · Intelligent Systems with Applications · doi:10.1016/j.iswa.2026.200677
Nguyen, H. T. (2026) · SSRN Electronic Journal · doi:10.2139/ssrn.6798854
Santiago, G., Cisdeli, P., Mandrini, G., Tuinstra, M. R., & Ciampitti, I. A. (2026) · The Plant Phenome Journal · doi:10.1002/ppj2.70087
The Impact of AI on Literary Analysis: Opportunities and Challenges
Priscilla, D. (2024) · International Journal of Scientific Research in Science and Technology · doi:10.32628/ijsrst24116520
Auditable LLM Autonomy for Operational Decision-Making: Big Data Evidence and Decision Traces
Theodorakopoulos, L., & Theodoropoulou, A. (2026) · Computers, materials & continua/Computers, materials & continua (Print) · doi:10.32604/cmc.2026.082270 · Cited by 7
“Replay designs should be explicit about what is frozen (evidence snapshots, configurations, ticket states) and what is re-derived at evaluation time (queries re-run against a versioned store, or approximated by stored retrieval results) [105].”
Huynh, T., Nguyen, M. L., Ha, H. T. T., & Ngo, L. T. (2026) · The Neuroradiology Journal · doi:10.1177/19714009261456608
Efficient conjugate gradient methods for unconstrained optimization and neural network applications
Hassan, B. A., Moghrabi, I. A. R., Ibrahim, A. L., Güler, N., & Jabbar, H. N. (2026) · OPSEARCH · doi:10.1007/s12597-026-01176-0
Papaioannou, C., Dimara, A., Papaioannou, A., & Krinidis, S. (2026) · Journal of Industrial Information Integration · doi:10.1016/j.jii.2026.101123
Chatterjee, R., & Haque, S. (2026) · International Conference on Recent Trends in Computer Science and Technology (ICRTCST) · doi:10.1109/icrtcst68392.2026.11545371
“The phishing attack that was previously introduced is an extremely challenging problem for defenders [9].”
Shrestha, R., Rana, M. M., Sun, B., Sun, F., Lou, H. H., & Hutson, A. (2026) · Sensors · doi:10.3390/s26123804
“Each model typically requires different preprocessing pipelines and dependencies, which increases operational overhead [1].”
InfluentialWhen Verification Becomes the Bottleneck: Automating Kubernetes Deployment Validation at ScalePreprint
Kathari, S. J. (2026) · Research Square · doi:10.21203/rs.3.rs-10012251/v1
Unlocking the Power of Knowledge Graphs
Azeroual, O. (2026) · IGI Global eBooks · doi:10.4018/979-8-3373-1360-3.ch002
From ITIL to AIOps in Public Sector: A Systematic Literature Review
Ganduri, C. (2026) · Journal of Engineering Research and Sciences · doi:10.55708/js0506005
“[8], [20]- [22] MLOps and ML engineering Lifecycle control, deployment readiness, monitoring, collaboration, and production maintenance.”
Udayakumar, M., Rathnasamy, S., & Kamaraj, K. (2026) · Future Generation Computer Systems · doi:10.1016/j.future.2026.108649 · Cited by 1
To Build or Not to Build? Factors that Lead to Non-Development or Abandonment of AI Systems
Chappidi, S., & Singh, J. (2026) · ACM Conference on Fairness, Accountability, and Transparency (FAccT) · doi:10.1145/3805689.3806736 · Cited by 1
“More specifically, problem formulation has been linked as an early AI development process shaping later, or downstream, stages of fairness assessment [75, 76, 121], ground truth construction [92, 111, 152], and performance evaluation [123, 160].”
Carrasco, H. A. O., & Hugo, R. O. (2026) · Arandu-UTIC. · doi:10.69639/arandu.v13i2.2252
Research on predictive maintenance of equipment based on artificial intelligence
Gao, X., You, Z., Wen, L., Gao, T., Jiang, K., & Cheng, Z. (2026) · Proceedings of the Institution of Mechanical Engineers Part C Journal of Mechanical Engineering Science · doi:10.1177/09544062261461705
“65 Although attempts have been made to use transfer learning methods to address this issue, satisfactory performance cannot be achieved in many scenarios in practice.”
Kataria, V., Kumar, N., & Chilakapati, G. (2026) · International journal of intelligent engineering and systems · doi:10.22266/ijies2026.0630.30
Comprehensive Review of Artificial Intelligence Applications in Project Management
Elmas, E. E. (2026) · Gazi Üniversitesi Fen Bilimleri Dergisi Part C Tasarım ve Teknoloji · doi:10.29109/gujsc.1923665
Challenges and ethical considerations in implementing Machine Learning
Galal, M. K., & Said, Z. (2026) · Elsevier eBooks · doi:10.1016/b978-0-443-33943-1.00003-4
Using Adaptive Activation Functions in Pre-Trained Artificial Neural Network Models
Bodyanskiy, Y. V., & Kostiuk, S. (2023) · International Conference on Information Control Systems & Technologies (ICST) · doi:10.55056/ceur-ws.org/vol-3513/paper8.pdf · Cited by 2
“Artificial neural network models have become essential to modern data processing systems [1].”
BackgroundA Conceptual Framework for AI-Driven Predictive Maintenance in Industrial Manufacturing Systems
Herath, S. K., & Yoo, J. K. (2026) · Advances in computational intelligence and robotics book series · doi:10.4018/979-8-3373-9725-2.ch002
Feng, R., Zhang, J., & Liu, J. J. (2026) · Sustainability · doi:10.3390/su18136606
Chen, M., Wu, J., Zhou, Y. W., Guo, X., Wang, N., Chen, Y., Li, X., & Qiu, A. (2026) · Analytica Chimica Acta · doi:10.1016/j.aca.2026.345912
Common sense testing and sanity checks in machine learning
Naser, M. Z. (2026) · International Journal of Data Science and Analytics · doi:10.1007/s41060-026-01183-w
“Thus, machine learning (ML) models often demonstrate strongperformanceunderwell-controlledtraining/validation regimens but may face substantial challenges once deployed (and even on trivial inquiries [2]) [3, 4].”
Cao, X., Qin, X., Zuo, Y., Fang, J., & WANG, H. (2026) · Carbon Balance and Management · doi:10.1186/s13021-026-00479-5
“The ML Technology Readiness Level (MLTRL) framework further provides structured quality criteria for each development stage, ensuring alignment with the unique demands of deployment [136].”
A data-centric trust pipeline:an empirical framework for trustworthy AI in sensitive domains
Pereira, C. D. C. (2026) · AI and Ethics · doi:10.1007/s43681-026-01247-4 · Cited by 1
“Paleyes et al. [28] survey case studies of ML systems in production and find that failures cluster at the boundaries between deployment stages: data collection feeds into validation, validation feeds into training, training feeds into monitoring, and each handoff is a documented site of friction.”
Labo-Popoola, O. A. (2026) · Applied Operations and Analytics · doi:10.1080/29966892.2026.2701487
Anuja Beatrice, B. (2024) · International Research Journal of Education and Technology (IRJET). · doi:10.70127/irjedt.vol.9.issue07.270
Soni, H., & Ramamurthy, P. (2023) · International Journal of Research Publications in Engineering Technology and Management · doi:10.15662/ijrpetm.2023.0601013 · Cited by 1
Big Data- and AI-Driven Hybrid Self-Attention Credit Scoring with Explainable Decisioning
Zakariya, G., Moldagulova, A., & Ali, N. B. (2026) · Big Data and Cognitive Computing · doi:10.3390/bdcc10070236
Ecosystem Constraints Affecting the Commercialization of Generative AI Startups
Kanatovna, S. A. (2026) · IEEE International Conference on Smart Information Systems and Technologies (SIST) · doi:10.1109/sist61674.2026.11596005
“The deployment of large generative models requires not only their initial training and subsequent retraining, but also the use of specialized equipment, which is characterized by high power consumption and complex software stacks [16].”
Efficient Self-Learning and Model Versioning for AI-native O-RAN Edge
Bensalem, M., Gentzen, F., Choong, T. W., Jhuang, Y.-C., Jukan, A., & Leu, J. (2026) · International Conference on Communications · doi:10.1109/icc59461.2026.11587660
“The past decade has witnessed an explosive growth in the size and complexity of ML models, accompanied by continual improvements in accuracy and robustness [3].”
Machine Learning Lifecycle: A Survey
Kosmas, I., Papadopoulos, T., & Michalakelis, C. (2026) · AppliedMath · doi:10.3390/appliedmath6070113
“Post-Production Monitoring Ad hoc, periodic manual data audits Automated, continuous telemetry; real-time drift detection [4,18,24] Retraining Trigger Manual when accuracy drops below the threshold Automated pipeline triggered by drift alerts [3,4,18] 4.2.”
InfluentialJEPA-Chain Engineering Framework: From Theory to Production Deployment in Blockchain Optimization
Hua, N. M., Phan, N. Q., Tran, A. C., & Huynh, H. X. (2026) · Lecture notes in computer science · doi:10.1007/978-981-92-2885-0_15
Zakariya, G., Moldagulova, A., & Ali, N. B. (2026) · AI · doi:10.3390/ai7070263
From MLOps to LLMOps: A Position on Engineering Discipline for AI-Native Applications
Mandadi, A. R. (2024) · International Journal of Scientific Research and Modern Technology. · doi:10.38124/ijsrmt.v3i4.1566
Integrating Traffic Density Analysis with Automated Violation Detection Through IoT Sensor Fussion
Chisom, C. A., Ezema, L. S., Benson, M. E., & Ezea, H. U. (2026) · Andalasian International Journal of Applied Science Engineering and Technology · doi:10.25077/aijaset.v6i2.328
“However, they are still helpful for quickly prototyping, connecting hardware, and conducting educational deployments because they are stable and easy to use with simulation tools like Proteus [20], [22].”
Theodorakopoulos, L., & Theodoropoulou, A. (2026) · Wiley Interdisciplinary Reviews Data Mining and Knowledge Discovery · doi:10.1002/widm.70116 · Cited by 3
A Scalable Lakehouse Architecture for AI-Driven Cybersecurity Intelligence
Farhadighalati, N., Giulio, A. D., Lusci, A., Valentini, R., & Barata, J. (2026) · International Young Engineers Forum (YEF-ECE) · doi:10.1109/yef-ece70590.2026.11614622
“Traditional MLOps often assumes that model performance remains relatively stable after deployment [14].”
Sujaka, T. T., Switrayana, I. N., & Fillah, I. M. H. (2025) · Building of Informatics Technology and Science (BITS) · doi:10.47065/bits.v7i3.8740
“…menunjukkan bahwa terdapat perbedaan yang signifikan antara apa yang berhasil di lingkungan akademis dan apa yang dibutuhkan oleh sistem dunia nyata[18] setelah mempelajari penelitian yang berkaitan tersebut, maka penelitian ini akan mengklasifikasikan 9 classes dari capsicum annuum dengan…”
Kimura, D. (2026) · SSRN Electronic Journal · doi:10.2139/ssrn.7010279
An Empirical Evaluation of AI Data Pipeline Architectures: A Registered ReportPreprint
Simon, E. I.-O., & de Carvalho, A. C. P. D. L. F. (2026) · SSRN Electronic Journal · doi:10.2139/ssrn.7078504
Narasimhan, V. (2026) · International Journal of Artificial Intelligence and Machine Learning · doi:10.51483/ijaiml.6.5s.2026.124-137
Enterprise Tax Systems Modernization Using Intelligent Integration Frameworks
MIRANI, A. (2026) · Computer Fraud & Security · doi:10.52710/cfs.1110
“_______________________________________________________________________________ 29 Vol: 2026 | Iss: 2 | 2026 [3].”
-, S. D. (2026) · International Journal of Artificial Intelligence and Machine Learning · doi:10.51483/ijaiml.6.5s.2026.488-496
Kirtac, K. (2026) · SSRN Electronic Journal · doi:10.2139/ssrn.7213792 · Cited by 1
Supervised Machine Learning for Classifying German Parliamentary Documents: A Comparative Study
Dorotsky, T., Wagler, R., Dietzmann, C., & Alt, R. (2026) · Lecture notes in networks and systems · doi:10.1007/978-3-032-32023-0_18
GreenAirOps: production-ready MLOps for real-time air quality index prediction
Goyal, S., Sharma, V., Hotchandani, V., Mahale, G., Gaikwad, M., & Shahade, A. K. (2026) · Air Quality Atmosphere & Health · doi:10.1007/s11869-026-02068-4
Backward Compatibility in Tree-Based Explanations and Enhanced CART Algorithm
Suzuki, H. (2026) · ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD) · doi:10.1145/3770855.3817736
Kilaru, S. (2026) · Lecture notes in networks and systems · doi:10.1007/978-3-032-31523-6_3
Méndez, Ó. A., & Flórez, H. (2026) · Communications in computer and information science · doi:10.1007/978-3-032-35635-2_8
Antonov, S. V. (2026) · American Journal of Interdisciplinary Research and Innovation · doi:10.54536/ajiri.v5i3.8120
“Paleyes et al. (2022) synthesized evidence from 209 machine learning deployment case studies and found that practitioners face challenges at every stage of the deployment workflow, from data engineering through model serving to monitoring and maintenance.”
InfluentialAn End to End Trustworthiness Evaluation Framework for Enterprise AI Systems
Muppidi, V. K. (2026) · Lecture notes in networks and systems · doi:10.1007/978-3-032-34789-3_22
A Microservices-Based Architecture for Machine Learning Systems Dedicated to Predictive Maintenance
Marchand, J., Laval, J., Sekhari, A., Cheutet, V., & Danielou, J.-B. (2026) · IEEE International Conference on Software Architecture Companion (ICSA-C) · doi:10.1109/icsa-c68850.2026.00011
“…from the requirements of a PdM service to its effective implementation presents significant challenges, not only in integrating ML models and establishing the necessary infrastructure [22], but also in ensuring continuous monitoring and maintenance of both the system and the ML models [17].”
Kassymova, A., Kabievna, U. R., Cho, Y. I., Venera, E. L. L. E., Anartayeva, A., & Smakhanova, A. (2026) · Applied Sciences · doi:10.3390/app16168129
Kandakatla, A. K. (2026) · International Journal of Computer Information Systems and Industrial Management Applications · doi:10.70917/ijcisim-2026-4743
Prause, M. (2026) · Systems · doi:10.3390/systems14081018 · Cited by 1
“These findings confirm earlier research indicating high failure rates in machine learning (ML) deployments [7][8].”
Xu, J., & Jia, X. (2026) · Wireless networks · doi:10.1007/978-3-032-30978-5_1
Sandhu, M. A., Nawaz, A., & Ahmad, A. (2026) · Journal of Open Innovation Technology Market and Complexity · doi:10.1016/j.joitmc.2026.100854
Developing Robust and Reproducible Machine Learning Systems
Polychronou, I., Nikolaou, G., & Patrikakis, C. Z. (2026) · IEEE Annual International Computer Software and Applications Conference (COMPSAC) · doi:10.1109/compsac69091.2026.00142
“As Machine Learning (ML) and Deep Learning (DL) models grow in complexity, deploying and maintaining them in production presents significant challenges [1], [2].”
A Real-Time Machine Learning Based Credit Card Fraud Detection System
Laboni, P., & Ogale, P. (2026) · IEEE Annual International Computer Software and Applications Conference (COMPSAC) · doi:10.1109/compsac69091.2026.00356
“This leaves financial institutions struggling to translate research prototypes into operational systems [4].”
Quantifying the Cost and Risk of Enterprise LLM Adaptation Strategies
Nisar, K. (2025) · International Journal of Research Publications in Engineering Technology and Management · doi:10.15662/ijrpetm.2025.08030012
Designing a Multi-Criteria Decision Framework for Enterprise Language Model Adaptation
Nisar, K. (2025) · International Journal of Science Research and Technology · doi:10.15662/ijsrat.2025.0806021 · Cited by 1
Bhaumik, U., & Berlin, M. A. (2026) · IEEE Access · doi:10.1109/access.2026.3726681
“The difficulty of operating ML systems—data drift, silent performance decay, and integration debt—is well documented [37], and a survey of deployment case studies confirms that practitioners hit obstacles at every stage of the pipeline [38].”
Kandakatla, A. K. (2026) · International Journal of Artificial Intelligence and Machine Learning · doi:10.51483/ijaiml.6.7s.2026.168-177
Behavioral Regression Testing for Continuously Updated Machine Learning Models
Pasupuleti, V., Songa, S., Gulkotwar, N., Allala, S. R., & Tyagi, S. (2026) · IEEE International Conference on Artificial Intelligence Testing (AITest) · doi:10.1109/aitest70988.2026.00030
“BRT-ML requires only (i) a retained holdout partition from the current deployment window, (ii) a fixed partition schema established at initial deployment, and (iii) stored reference model signatures σ i computed once per baseline model [17].”
FitRAG: Self-Improving LLM-Based Services through Feedback-Driven Adapter Lifecycle Management
Syah, R. A., Haryanto, C. Y., Lomempow, E., Malik, K., & Putra, I. (2026) · IEEE International Conference on Software Services Engineering (SSE) · doi:10.1109/sse72781.2026.00022
“Paleyes et al. [21] survey deployment challenges across industries and document that ML introduces artifacts with characteristics unlike source code: model weights and datasets cannot be versioned, reviewed, or delivered using standard SE tooling, and deployed systems change along three axes of…”
Evaluating DevOps, DevSecOps, MLOps and CloudOps–Results from an Adapted MLR
Yakushenko, A., McCann, R., Hughes, C., McElligott, S., Yılmaz, M., MacMahon, S. T., Mccarren, A., & McCarren, A. L. (2026) · Communications in computer and information science · doi:10.1007/978-3-032-36813-3_6
Toward Intelligent Infrastructure: MAIA, a Modular AI Architecture for Industrial Control Systems
Slunjski, M. (2026) · IEEE Access · doi:10.1109/access.2026.3728856
“For more information, see https://creativecommons.org/licenses/by-nc-nd/4.0/ energy management and process optimisation report benefits such as predictive maintenance and adaptive scheduling, yet many frameworks are process-specific and difficult to generalise [2], [3], [4].”
InfluentialAlieme, J. I., Sule, A., & Obukadata, V. O. (2026) · Gulf Journal of Computer Sciences · doi:10.51594/gjcs.v1i4.217 · Cited by 3
A Governance Framework For Trustworthy AI-Generated Data Engineering Artifacts In Cloud Environments
Kodati, P. K. (2026) · International Journal of Artificial Intelligence and Machine Learning · doi:10.51483/ijaiml.6.8s.2026.86-96
Evaluating White-Box Adversarial Attacks on Encrypted DGA and DNS Tunneling Detection
Elizalde, S., AlSabeh, A., Mazloum, A., Galán–Jiménez, J., Kfoury, E. F., & Crichigno, J. (2026) · IEEE/IFIP Network Operations and Management Symposium (NOMS) · doi:10.1109/noms69089.2026.11668195
“However, as ML becomes a core component of Network Intrusion Detection System (NIDS), it also becomes part of the attack surface, introducing new risks [5].”
Lopez, M. M. (2026) · Advances in computational intelligence and robotics book series · doi:10.4018/979-8-3373-9200-4.ch012
Li, F.-Z., Xu, Q.-R., Zhou, T., Wang, C.-X., Wang, Y.-F., & Peng, X.-H. (2026) · Journal of Computational Science and Technology · doi:10.1007/s11390-026-6073-4
Hong, G., Lu, Y., & Cho, H. (2026) · The International Journal of Advanced Manufacturing Technology · doi:10.1007/s00170-026-19015-3
Varma, D., Parmar, R., Bhat, S., & Dutta, P. (2026) · Future Generation Computer Systems · doi:10.1016/j.future.2026.108807
Nguyen, T. M., & Chew, J. W. (2026) · Fuel · doi:10.1016/j.fuel.2026.141198
Marimuthu, G. (2026) · IEEE International Conference on Information Reuse and Integration (IRI) · doi:10.1109/iri69576.2026.00013
“Software reuse has long been recognized as essential for managing complexity [8].”
Metadata
- Authors
- Paleyes, A., Urma, R.-G., & Lawrence, N. D.
- Affiliations
- University of Cambridge (GB)
- Cambridge Spark, Cambridge, United Kingdom
- Venue
- ACM Computing Surveys
- Published
- 2022-12-07
- Volume
- 55
- Issue
- 6
- Pages
- 1-29
- ISSN
- 0360-0300 (ISSN-L)
- 1557-7341
- OpenAlex
- W3104128335
- Semantic Scholar
- b1f574c47d0b6e3032246770b9cbebb9c7bd0c7f
- Cited by
- 638
- References
- 128
- Citations by year
- 2026: 149 · 2025: 156 · 2024: 166 · 2023: 93 · 2022: 46
- FWCI
- 114.17
- Type
- journal article
- Language
- en
- Open access
- hybrid
- doi.org
- Licence
- Locations
- ACM Computing Surveys (publishedVersion, cc-by)
- arXiv (Cornell University) (submittedVersion)
- White Rose Research Online (University of Leeds, The University of Sheffield, University of York) (submittedVersion)
- Apollo (University of Cambridge) (submittedVersion)
- arXiv (Cornell University)
- Apollo
- Funders
- Alan Turing Institute
- UK Research & Innovation
- Topics
- Physical Sciences › Computer Science › Information Systems › Software Engineering Techniques and Practices
- Physical Sciences › Computer Science › Artificial Intelligence › Artificial Intelligence Applications
- Physical Sciences › Computer Science › Information Systems › Cloud Computing and Resource Management
- Keywords
- machine learning deployment, production systems, deployment challenges, industry case studies
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.