MétaCan
Menu
Back to cohort
Record W4410381405 · doi:10.48175/ijarsct-19200a

Optimized Deployment of Multi-Objective Machine Learning Models in Azure ML: A Compliance-Driven and Cost-Conscious Pipeline Framework

2024· article· en· W4410381405 on OpenAlexaff
Dheerendra Yaganti

Bibliographic record

VenueInternational Journal of Advanced Research in Science Communication and Technology · 2024
Typearticle
Languageen
FieldDecision Sciences
TopicScientific Computing and Data Management
Canadian institutionsASTER
Fundersnot available
KeywordsSoftware deploymentPipeline (software)Compliance (psychology)Computer scienceArtificial intelligenceMachine learningSoftware engineeringOperating systemPsychologySocial psychology

Abstract

fetched live from OpenAlex

The growing complexity of enterprise-grade machine learning (ML) applications demands deployment pipelines that balance performance, compliance, and cost-efficiency. This paper presents a novel framework for the optimized deployment of multi-objective ML models using Azure Machine Learning (Azure ML). The proposed system integrates model evaluation metrics such as prediction accuracy, inference latency, and regulatory compliance scoring to enable intelligent deployment decisions. A cost-aware pipeline is constructed using Azure Pipelines, enabling conditional model promotion across development, staging, and production environments. Compliance alignment is validated through Azure Policy, integrated into the ML workflow to enforce data residency, algorithm transparency, and audit-readiness. Key components of the system include MLflow for experiment tracking, Azure Kubernetes Service (AKS) for scalable inference, and Azure Cost Management for continuous cost analysis. Furthermore, the pipeline incorporates model interpretability tools and automated drift detection to maintain deployment integrity over time. Through rigorous experimentation on classification and regression tasks, the framework demonstrates improvements in deployment efficiency, governance adherence, and cloud resource utilization. This paper offers a reproducible blueprint for organizations aiming to implement secure, cost-effective, and regulation-compliant ML model deployment in cloud-native environments.

Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.

How this classification was reachedexpand

Full frame distilled prediction

Teacher imitation

Not calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.

metaresearch head score (Codex)0.012
metaresearch head score (Gemma)0.007
Version: codex-gemma-dda1882f352aValidation status: machine_predicted_unvalidated
Candidate categoriesnone
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Simulation or modeling · Consensus signal: none
GenreCandidate signal: Empirical · Consensus signal: Empirical
Teacher disagreement score0.806
Threshold uncertainty score0.800

Codex and Gemma teacher scores by category

CategoryCodexGemma
Metaresearch0.0120.007
Meta-epidemiology (narrow)0.0000.000
Meta-epidemiology (broad)0.0000.000
Bibliometrics0.0040.003
Science and technology studies0.0000.002
Scholarly communication0.0000.001
Open science0.0020.002
Research integrity0.0000.001
Insufficient payload (model declined to judge)0.0000.000

Machine scores (provisional)

The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.

Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.

Opus teacher head0.264
GPT teacher head0.514
Teacher spread0.250 · how far apart the two teachers sit on this one work
Validation statusscore_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it

Classification

machine, unvalidated

Machine predicted; a candidate call from one teacher head, not a consensus.

The models applied no category: nothing in the taxonomy fit this work.
Study designSimulation or modeling
Domainnot available
GenreEmpirical

How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".

Quick stats

Citations0
Published2024
Admission routes1
Has abstractyes

Explore more

Same venueInternational Journal of Advanced Research in Science Communication and TechnologySame topicScientific Computing and Data ManagementFrench-language works237,207