CogSciK: Clustering for Cognitive Science Motivated Decision Making

TL;DR

CogSciK is an unsupervised clustering algorithm inspired by cognitive science that classifies decision points based on an actor’s orientation, aiding decision-making models in complex contexts.

Contribution

The paper introduces CogSciK, a novel clustering algorithm grounded in cognitive science theory for modeling decision-making processes.

Findings

Enables unsupervised classification of decision points

Incorporates cognitive science principles into clustering

Provides a core-periphery structure for decision likelihood

Abstract

Computational models of decisionmaking must contend with the variance of context and any number of possible decisions that a defined strategic actor can make at a given time. Relying on cognitive science theory, the authors have created an algorithm that captures the orientation of the actor towards an object and arrays the possible decisions available to that actor based on their given intersubjective orientation. This algorithm, like a traditional K-means clustering algorithm, relies on a core-periphery structure that gives the likelihood of moves as those closest to the cluster's centroid. The result is an algorithm that enables unsupervised classification of an array of decision points belonging to an actor's present state and deeply rooted in cognitive science theory.