Operationalization of Machine Learning with Serverless Architecture: An Industrial Operationalization of Machine Learning with Serverless Architecture: An Industrial Implementation for Harmonized System Code Prediction

TL;DR

The paper tackles automating HS code classification in global trade by deploying a serverless MLOps framework that orchestrates data ingestion, training, deployment, monitoring, and retraining. It compares classical SVC, LSTM, DNN, and Text-CNN approaches, showing that Text-CNN with a custom embedding outperforms others with an overall accuracy of 98% and strong performance on minority classes, especially after stratified up-sampling; automated A/B testing guides model promotion. A key contribution is a replicable, cost-conscious blueprint for industrial ML operationalization using serverless infrastructure, including reproducible pipelines, auto-scaling, and governance-centric features. The work demonstrates a practical, scalable pathway to deterministic, auditable HS code predictions with low latency, enabling enterprises to scale compliant cross-border classification while controlling operational expenses and risk.

Abstract

This paper presents a serverless MLOps framework orchestrating the complete ML lifecycle from data ingestion, training, deployment, monitoring, and retraining to using event-driven pipelines and managed services. The architecture is model-agnostic, supporting diverse inference patterns through standardized interfaces, enabling rapid adaptation without infrastructure overhead. We demonstrate practical applicability through an industrial implementation for Harmonized System (HS) code prediction, a compliance-critical task where short, unstructured product descriptions are mapped to standardized codes used by customs authorities in global trade. Frequent updates and ambiguous descriptions make classification challenging, with errors causing shipment delays and financial losses. Our solution uses a custom text embedding encoder and multiple deep learning architectures, with Text-CNN achieving 98 percent accuracy on ground truth data. Beyond accuracy, the pipeline ensures reproducibility, auditability, and SLA adherence under variable loads via auto-scaling. A key feature is automated A/B testing, enabling dynamic model selection and safe promotion in production. Cost-efficiency drives model choice; while transformers may achieve similar accuracy, their long-term operational costs are significantly higher. Deterministic classification with predictable latency and explainability is prioritized, though the architecture remains extensible to transformer variants and LLM-based inference. The paper first introduces the deep learning architectures with simulations and model comparisons, then discusses industrialization through serverless architecture, demonstrating automated retraining, prediction, and validation of HS codes. This work provides a replicable blueprint for operationalizing ML using serverless architecture, enabling enterprises to scale while optimizing performance and economics.

Figures (8)

• Figure 1: Distribution of assurance levels in the training data
• Figure 2: Text length (number of characters) for combined description in training data
• Figure 3: Class Imbalance as seen on training data
• Figure 4: Top to Bottom: Architecture Diagram for LSTM, DNN and Text-CNN Model (Specifications in the diagram are the same as those used in the experimentation)
• Figure 5: Machine learning model life-cycle