Decision-Value Attribution in Predict-then-Optimize Systems
2026-06-29 • Machine Learning
Machine Learning
AI summaryⓘ
The authors highlight that explaining predictions alone isn’t enough when those predictions lead to decisions through optimization. They introduce Decision Value Attribution (DVA), a method that breaks down how different features or design choices affect the actual value of decisions made by combining predictions with optimization. Their approach can separately assess the impact of information and system settings, and helps check if predicted benefits match real-world results. They tested this on problems like energy storage and emergency services, showing that traditional explanations often miss what really matters for decision outcomes.
Predict-then-optimizeShapley valuesDecision valueFeature attributionOperational decision-makingOptimization configurationsElectricity storage arbitrageEmergency medical service coveragePredictive modelingDecision diagnostics
Authors
Konstantinos Ziliaskopoulos, Alexander Vinel, Alice E. Smith
Abstract
Predictive models are increasingly embedded in operational decision-making, yet standard explanation methods typically explain forecasts rather than the decisions those forecasts induce. This distinction is important in predict-then-optimize systems: large forecast changes may leave the optimizer's action unchanged, while small changes can alter the selected decision and its realized value. We propose Decision Value Attribution (DVA), a Shapley-based framework for attributing the value of a fixed prediction--optimization pipeline. The framework defines cooperative games whose payoff is the downstream decision value, allowing the players to be information sources, optimization or design parameters, or both. We present three variants: InfoDVA attributes value to features, DesignDVA attributes value to operational configurations, and Decision-Value Interactions (DVI) quantifies how information and design jointly create value. We further distinguish post-DVA, which evaluates decisions using realized outcomes, from pre-DVA, which evaluates decisions under the model's full prediction. This separation turns attribution into a decision-level diagnostic of whether the model's operational beliefs align with realized performance. The resulting attributions are expressed in the units of the operational objective and decompose the gain or loss relative to a baseline. Case studies in electricity storage arbitrage and emergency medical service coverage show that predictive explanations can be poor proxies for operational value, that DVA can guide targeted information-control interventions, and that optimization configurations determine when predictive information is decision-relevant.