Beyond Predictions: A Participatory Framework for Multi-Stakeholder Decision-Making

2025-02-12

AI Summary

To address the challenge that conventional supervised decision support systems struggle to reconcile conflicting preferences among multiple stakeholders, this paper proposes a preference-driven participatory decision-making framework. Methodologically, it formalizes decision-making as a contextualized multi-objective optimization problem, introducing (i) a reward-function-based stakeholder representation mechanism, (ii) a model-agnostic and interpretable modular architecture, and (iii) a dynamic trade-off and consensus-generation mechanism integrating compromise functions with user-defined composite scoring. Experiments on two real-world scenarios demonstrate that the framework significantly outperforms pure predictive baselines in balancing competing objectives. Ablation studies confirm its robustness across diverse models, scales, and domains. The core contribution is the first general-purpose, multi-stakeholder decision support paradigm that simultaneously ensures interpretability, flexibility, and consensus orientation.

Technology Category

• Knowledge Representation and Reasoning: Preferences
• Humans and AI: Planning and Decision Support for Human-Machine Teams
• Machine Learning: Learning Preferences or Rankings

Application Category

• User Modeling, Personalization and Recommendation: Explainable and interpretable methods for personalization
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Responsible Web: Machine-in-the-loop, human agency and autonomy

Abstract

Conventional decision-support systems, primarily based on supervised learning, focus on outcome prediction models to recommend actions. However, they often fail to account for the complexities of multi-actor environments, where diverse and potentially conflicting stakeholder preferences must be balanced. In this paper, we propose a novel participatory framework that redefines decision-making as a multi-stakeholder optimization problem, capturing each actor's preferences through context-dependent reward functions. Our framework leverages $k$-fold cross-validation to fine-tune user-provided outcome prediction models and evaluate decision strategies, including compromise functions mediating stakeholder trade-offs. We introduce a synthetic scoring mechanism that exploits user-defined preferences across multiple metrics to rank decision-making strategies and identify the optimal decision-maker. The selected decision-maker can then be used to generate actionable recommendations for new data. We validate our framework using two real-world use cases, demonstrating its ability to deliver recommendations that effectively balance multiple metrics, achieving results that are often beyond the scope of purely prediction-based methods. Ablation studies demonstrate that our framework, with its modular, model-agnostic, and inherently transparent design, integrates seamlessly with various predictive models, reward structures, evaluation metrics, and sample sizes, making it particularly suited for complex, high-stakes decision-making contexts.

Problem

• Multi-stakeholder optimization
• Balancing conflicting preferences
• Enhancing decision-making beyond prediction

Innovation

• Multi-stakeholder optimization problem
• K-fold cross-validation fine-tuning
• Synthetic scoring mechanism