Bank Run, Interrupted: Modeling Deposit Withdrawals with Generative AI
Management Science · 06.07.2026
DOI: 10.1287/mnsc.2024.06807 ↗Kurz gefasst
Fachartikel in der Zeitschrift Management Science, online erschienen am 06.07.2026. Verfasst von Sophia Kazinnik. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 41 Literaturangaben.
Abstract (Originalsprache)
I study depositor behavior in panic-driven bank runs using an LLM-based survey simulation. I build a representative population of synthetic agents by assigning demographic attributes, expose them to a viral panic post, and randomize bank communication interventions. I validate model responses against human benchmarks and then generate systematic message variants that vary tone, strength, and content within the validated design space. I then include the estimated withdrawal propensities into a contagion model, which maps network nodes to depositor personas and propagates withdrawals through a single layer proximity network. Direct, personalized bank communications with strong reassurances and explicit survival clauses substantially reduce withdrawal intent. This framework offers an efficient, inexpensive method for testing crisis messages and projecting how runs may unfold under alternative communication strategies. This paper was accepted by Kay Giesecke, finance. Supplemental Material: The online appendix and data files are available at https://doi.org/10.1287/mnsc.2024.06807 .
Zitieren
APA
Kazinnik, S. (2026). Bank Run, Interrupted: Modeling Deposit Withdrawals with Generative AI. Management Science. https://doi.org/10.1287/mnsc.2024.06807
Vancouver
Kazinnik S. Bank Run, Interrupted: Modeling Deposit Withdrawals with Generative AI. Management Science. 2026. doi:10.1287/mnsc.2024.06807
BibTeX
@article{Kazinnik2026,
author = {Kazinnik, Sophia},
title = {Bank Run, Interrupted: Modeling Deposit Withdrawals with Generative AI},
journal = {Management Science},
year = {2026},
doi = {10.1287/mnsc.2024.06807}
}
EUVIMED