Abstract 

Everyday choices are guided by qualitative, context-rich reasons, yet such reasons have been difficult to formalize within standard models of choice.  As a result, choice modeling in the behavioral sciences has largely focused on abstract, highly stylized problems that diverge sharply from the consequential decisions people routinely face in their lives. We introduce a computational framework that uses latent representations from large language models (LLMs) to quantify the semantic content of reasons. The framework maps any expressed decision-relevant consideration onto a vector representation in a multidimensional space, enabling direct integration with established multiattribute theories of decision making. We show that our approach can be used to accurately predict naturalistic choices, characterize individual differences in terms of decision weights over reasons, and formalize the role of memory and attention processes in the retrieval and aggregation of reasons during deliberation. We also apply our framework to a new dataset of over 100K descriptions of real-world choices, revealing the reasons that guide important life decisions and how they vary across individuals and situations. Overall, our work combines the representational power of LLMs with established models in psychology, economics, neuroscience, and marketing, enabling the formal analysis of everyday choices, and the processes that shape them, at scale.

To attend, please contact us at dip.mkt@unibocconi.it