Prescriptive Artificial Intelligence: A Formal Paradigm for Auditing Human Decisions Under Uncertainty

TL;DR

This paper introduces Prescriptive AI as a new paradigm for human-AI collaboration in high-stakes decisions, emphasizing normative guidance and accountability over mere outcome prediction.

Contribution

It formalizes prescriptive systems with axioms, proves fundamental separation results, and demonstrates a practical fuzzy inference system for decision auditing.

Findings

Supervised learning cannot correct systematic biases without external normative signals.

Performance in decision imitation is limited by structural bias, not just data size.

The framework is applicable to safety-critical domains requiring interpretability and normative alignment.

Abstract

We formalize Prescriptive Artificial Intelligence as a distinct paradigm for human-AI decision collaboration in high-stakes environments. Unlike predictive systems optimized for outcome accuracy, prescriptive systems are designed to recommend and audit human decisions under uncertainty, providing normative guidance while preserving human agency and accountability. We introduce four domain-independent axioms characterizing prescriptive systems and prove fundamental separation results. Central among these is the Imitation Incompleteness theorem, which establishes that supervised learning from historical decisions cannot correct systematic decision biases in the absence of external normative signals. Consequently, performance in decision imitation is bounded by a structural bias term epsilon_bias rather than the statistical learning rate O(1/sqrt(n)). This result formalizes the empirically observed accuracy ceiling in human decision imitation tasks and provides a principled criterion for when automation should be replaced by epistemic auditing. We demonstrate the computational realizability of the framework through an interpretable fuzzy inference system, applied as a stress test in elite soccer decision-making, where it reveals systematic decision latency and risk states obscured by outcome and status quo biases. The proposed framework establishes Prescriptive AI as a general, realizable class of decision-support systems applicable across safety-critical domains in which interpretability, contestability, and normative alignment are essential.