Using Observational Counterfactual Explanations to improve Sequential Decision-Making

Abdirisak Mohamed

Abstract:

Human decision-making is plagued by a consider-
able amount of noise. In this work, we utilize the

flexibility of observational (backtracking) counter-
factual explanations to support the diagnostic pro-
cess in sequential decision-making. In particular,

we explore how this approach can be effectively
employed when decisions are influenced solely by
external factors like the decision maker’s fatigue
levels, or personal biases. By exploring these
counterfactual explanations, we aim to strength
trust in the decision-making process.