Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Representations of epistemic uncertainty and awareness in data-driven strategies

Mario Angelelli, Massimiliano Gervasi

TL;DR

The paper tackles epistemic uncertainty in data-driven strategies arising from bounded data observability and agent-mediated knowledge transfer. It introduces an order-theoretic, dimensional-framework for representing knowledge states (inner states) and their updates (meta-states and ν-meta-states), with explainability defined as the existence of diagonal compositions. By drawing analogies to Ellsberg's ambiguity and Wigner's Friend, the authors illustrate observer-dependent uncertainty and non-classical reasoning in data-driven contexts. The framework aims to guide assessment and measurement tool design for business value and maturity, and points to future work at the intersection of information geometry and non-classical uncertainty modeling to improve measurement of data-driven value chains.

Abstract

The diffusion of AI and big data is reshaping decision-making processes by increasing the amount of information that supports decisions while reducing direct interaction with data and empirical evidence. This paradigm shift introduces new sources of uncertainty, as limited data observability results in ambiguity and a lack of interpretability. The need for the proper analysis of data-driven strategies motivates the search for new models that can describe this type of bounded access to knowledge. This contribution presents a novel theoretical model for uncertainty in knowledge representation and its transfer mediated by agents. We provide a dynamical description of knowledge states by endowing our model with a structure to compare and combine them. Specifically, an update is represented through combinations, and its explainability is based on its consistency in different dimensional representations. We look at inequivalent knowledge representations in terms of multiplicity of inferences, preference relations, and information measures. Furthermore, we define a formal analogy with two scenarios that illustrate non-classical uncertainty in terms of ambiguity (Ellsberg's model) and reasoning about knowledge mediated by other agents observing data (Wigner's friend). Finally, we discuss some implications of the proposed model for data-driven strategies, with special attention to reasoning under uncertainty about business value dimensions and the design of measurement tools for their assessment.

Representations of epistemic uncertainty and awareness in data-driven strategies

TL;DR

The paper tackles epistemic uncertainty in data-driven strategies arising from bounded data observability and agent-mediated knowledge transfer. It introduces an order-theoretic, dimensional-framework for representing knowledge states (inner states) and their updates (meta-states and ν-meta-states), with explainability defined as the existence of diagonal compositions. By drawing analogies to Ellsberg's ambiguity and Wigner's Friend, the authors illustrate observer-dependent uncertainty and non-classical reasoning in data-driven contexts. The framework aims to guide assessment and measurement tool design for business value and maturity, and points to future work at the intersection of information geometry and non-classical uncertainty modeling to improve measurement of data-driven value chains.

Abstract

The diffusion of AI and big data is reshaping decision-making processes by increasing the amount of information that supports decisions while reducing direct interaction with data and empirical evidence. This paradigm shift introduces new sources of uncertainty, as limited data observability results in ambiguity and a lack of interpretability. The need for the proper analysis of data-driven strategies motivates the search for new models that can describe this type of bounded access to knowledge. This contribution presents a novel theoretical model for uncertainty in knowledge representation and its transfer mediated by agents. We provide a dynamical description of knowledge states by endowing our model with a structure to compare and combine them. Specifically, an update is represented through combinations, and its explainability is based on its consistency in different dimensional representations. We look at inequivalent knowledge representations in terms of multiplicity of inferences, preference relations, and information measures. Furthermore, we define a formal analogy with two scenarios that illustrate non-classical uncertainty in terms of ambiguity (Ellsberg's model) and reasoning about knowledge mediated by other agents observing data (Wigner's friend). Finally, we discuss some implications of the proposed model for data-driven strategies, with special attention to reasoning under uncertainty about business value dimensions and the design of measurement tools for their assessment.

Paper Structure

This paper contains 28 sections, 24 equations, 3 figures, 1 table.

Table of Contents

  1. Introduction
  2. Motivations
  3. Scope of the work
  4. Preliminaries on uncertainty scenarios
  5. Uncertainty types in data-driven strategies
  6. Ambiguity: urn models
  7. Lack of observability: Wigner's Friend
  8. Evidence of non-classical behaviour in cognition and self-assessment
  9. From Dimensional frameworks to Dimensional structures
  10. State of the art
  11. Dimensional frameworks as state transitions
  12. Model proposal: operational aspects of knowledge representations
  13. Comparison, composition, and the role of observers: inner states
  14. Self-reference
  15. Explainability as compositional existence
  16. ...and 13 more sections

Figures (3)

  • Figure 1: Diagrammatic representation of Ellsberg's three-colour model compared to the relation of human and artificial agents with data.
  • Figure 2: Representations of ambiguity in Ellsberg's three-colour model using the two types of meta-states. Dashed lines (left figure) distinguish pairs in the poset $\varrho^{\star}$ that do not belong to the poset $\varrho_{\star}$. Dotted lines (right figure) depict the map $\nu$ linking $\varrho^{\star}$ to the Boolean algebra $V_{\text{exp}}:=\mathtt{B}^{(1)}$.
  • Figure 3: Diagrammatic representation of a Wigner's friend scenario describing a high-level interaction of human and artificial agents in a data-driven scenario.

Theorems & Definitions (12)

  • Definition 1
  • Example 1
  • Definition 2
  • Remark 1
  • Remark 2
  • Definition 3
  • Definition 4
  • Definition 5
  • Remark 3
  • Example 2
  • ...and 2 more