ASTER: Adaptive Spatio-Temporal Early Decision Model for Dynamic Resource Allocation

2025-06-22

AI Summary

To address the challenge of premature decision-making in dynamic resource allocation, this paper proposes an end-to-end spatiotemporal intelligence framework that unifies event forecasting and actionable policy generation—breaking away from the conventional decoupled “prediction-then-decision” paradigm. Methodologically, we design a Resilient Adaptive Spatiotemporal (RaST) interaction module to capture both long- and short-term dependencies, and introduce a Preference-oriented Decision Agent (Poda) that jointly integrates resource-aware modeling, multi-objective reinforcement learning, and dynamic preference optimization—enabling co-optimization of prediction accuracy and policy feasibility under evolving resource constraints. Evaluated on four benchmark datasets across six downstream metrics, our approach achieves state-of-the-art performance, significantly improving early-event prediction accuracy and resource allocation efficiency. To the best of our knowledge, this is the first work to realize holistic, joint optimization of forecasting and decision-making in dynamic resource allocation.

Technology Category

• Planning, Routing, and Scheduling: Optimization of Spatio-temporal Systems
• Reasoning under Uncertainty: Sequential Decision Making
• Humans and AI: Human-Aware Planning and Behavior Prediction

Application Category

• Responsible Web: Machine-in-the-loop, human agency and autonomy
• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking
• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs

Abstract

Supporting decision-making has long been a central vision in the field of spatio-temporal intelligence. While prior work has improved the timeliness and accuracy of spatio-temporal forecasting, converting these forecasts into actionable strategies remains a key challenge. A main limitation is the decoupling of the prediction and the downstream decision phases, which can significantly degrade the downstream efficiency. For example, in emergency response, the priority is successful resource allocation and intervention, not just incident prediction. To this end, it is essential to propose an Adaptive Spatio-Temporal Early Decision model (ASTER) that reforms the forecasting paradigm from event anticipation to actionable decision support. This framework ensures that information is directly used for decision-making, thereby maximizing overall effectiveness. Specifically, ASTER introduces a new Resource-aware Spatio-Temporal interaction module (RaST) that adaptively captures long- and short-term dependencies under dynamic resource conditions, producing context-aware spatiotemporal representations. To directly generate actionable decisions, we further design a Preference-oriented decision agent (Poda) based on multi-objective reinforcement learning, which transforms predictive signals into resource-efficient intervention strategies by deriving optimal actions under specific preferences and dynamic constraints. Experimental results on four benchmark datasets demonstrate the state-of-the-art performance of ASTER in improving both early prediction accuracy and resource allocation outcomes across six downstream metrics.

Problem

• Converts spatio-temporal forecasts into actionable resource allocation strategies
• Integrates prediction and decision phases to enhance downstream efficiency
• Optimizes dynamic resource allocation under specific preferences and constraints

Innovation

• Adaptive Spatio-Temporal Early Decision model
• Resource-aware Spatio-Temporal interaction module
• Preference-oriented decision agent with reinforcement learning