Data-Driven Stochastic Modeling Using Autoregressive Sequence Models: Translating Event Tables to Queueing Dynamics

2025-09-06

AI Summary

Conventional queueing network modeling relies on manually specified arrival, service, and routing mechanisms, limiting scalability and accessibility. Method: We propose a data-driven autoregressive sequence modeling framework that reformulates queueing system modeling as joint learning of event-type and inter-event time distributions. Leveraging the Transformer architecture in an end-to-end manner, our approach requires no prior assumptions or explicit process design, while enabling uncertainty quantification and counterfactual intervention analysis. Contribution/Results: Evaluated on diverse synthetic queueing network event logs, our method faithfully reproduces dynamic system behavior, accurately characterizes predictive uncertainty, and effectively assesses policy intervention impacts. It significantly advances automated queueing model construction and enhances applicability across real-world service scenarios.

Technology Category

• Planning, Routing, and Scheduling: Model-Based Reasoning
• Machine Learning: Calibration & Uncertainty Quantification
• Reasoning under Uncertainty: Sequential Decision Making

Application Category

• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• User Modeling, Personalization and Recommendation: Attacks and countermeasures in recommendation systems
• Responsible Web: Machine-in-the-loop, human agency and autonomy

Abstract

While queueing network models are powerful tools for analyzing service systems, they traditionally require substantial human effort and domain expertise to construct. To make this modeling approach more scalable and accessible, we propose a data-driven framework for queueing network modeling and simulation based on autoregressive sequence models trained on event-stream data. Instead of explicitly specifying arrival processes, service mechanisms, or routing logic, our approach learns the conditional distributions of event types and event times, recasting the modeling task as a problem of sequence distribution learning. We show that Transformer-style architectures can effectively parameterize these distributions, enabling automated construction of high-fidelity simulators. As a proof of concept, we validate our framework on event tables generated from diverse queueing networks, showcasing its utility in simulation, uncertainty quantification, and counterfactual evaluation. Leveraging advances in artificial intelligence and the growing availability of data, our framework takes a step toward more automated, data-driven modeling pipelines to support broader adoption of queueing network models across service domains.

Problem

• Automating queueing network model construction from data
• Learning event distributions using autoregressive sequence models
• Enabling scalable simulation without manual parameter specification

Innovation

• Autoregressive models learn event distributions from data
• Transformers parameterize queueing dynamics without manual specification
• Data-driven framework automates high-fidelity simulation construction