Active learning as a means to distinguish among prominent decision strategies

Abstract

A long-standing debate in decision making has been whether people rely on very little information for making choices, or weigh and add all available information. We propose a new method to determine whether a non-compensatory (Take-The-Best) or compensatory strategy (Logistic Regression) is more psychologically plausible: by looking at people’s active learning queries. This method goes beyond traditional model selection techniques as it reveals the information people choose to learn early on, which subsequently drives their decisions. We developed active learning algorithms for both Take-The-Best and logistic regression and designed an active learning experiment to psychologically distinguish between these two models. Letting both models and humans actively learn and then comparing their queries, we found that people follow a rank-based learning strategy in non-compensatory environments and prefer more certainty-based queries in compensatory environments. The potential for active learning studies to further tease apart different models of decision making will be discussed.


Back to Table of Contents