Using AI to Let History Speak About Bank Runs
Banking crises are generally related to financial institution runs and banking panics, but our empirical understanding of financial institution runs is constrained by a scarcity of bank-level information. In a new paper, we use giant language fashions (LLMs) to extract data on financial institution runs from tens of millions of digitized historic newspaper pages, creating probably the most complete database of financial institution runs in U.S. historical past. Each financial institution run episode that we establish is documented on a companion website the place customers can browse and look at particular person episodes, and browse the unique newspaper articles. On this publish, we describe how we constructed this dataset and focus on what its fundamental options reveal.
How Newspapers Can Assist Us to Perceive Financial institution Runs
Till the tip of the acute section of the Nice Despair in 1933, financial institution runs have been a recurring characteristic of American financial life. Nevertheless, they left few traces in official data. Historic regulatory filings, such as those from the Office of the Comptroller of the Currency, doc when a financial institution closed its doorways. However such data don’t point out whether or not a run occurred earlier than failure. Equally, there are not any systematic data that doc episodes when a financial institution was topic to a run however however continued working and thus by no means appeared in any regulatory checklist of financial institution closures.
In our new paper, we try to beat this problem by extracting data on financial institution misery occasions from historic newspapers. We exploit that the Library of Congress’s Chronicling America challenge has digitized tens of tens of millions of historic newspaper articles. This archive is a treasure trove for financial historians and comprises an infinite quantity of knowledge. Though its sheer scale presents a problem, advances in giant language fashions and computing energy have made such historic data accessible to researchers. Within the following, we describe how we make this huge database communicate to us about financial institution runs.
Letting the Newspapers Communicate
For our evaluation, we begin with a physique of greater than 374 million newspaper articles (Dell et al., 2023). To reach at a structured dataset that allows us to research the knowledge content material of the newspaper articles systematically, we construct a knowledge extraction pipeline. We first search the digitized newspaper archives for articles mentioning particular banks along side a wide range of key phrases suggesting monetary misery like “financial institution run,” “deposit withdrawals,” “suspended,” and “closed its doorways.” This preliminary key phrase search reduces the set of 374 million articles to a smaller set of about one million “candidate articles.”
Then we feed every candidate article to numerous LLMs and immediate these fashions to extract structured data: Which financial institution is described? What occurred? Was there a depositor run, a suspension of funds, a closure, a reopening? When did every occasion happen? We additionally ask the fashions to categorise how the financial institution responded to the run, if one occurred. Did the financial institution obtain assist from a clearinghouse? Did it make a public show of solvency? Did shareholders inject new capital? What brought about the run within the first place? Was it pushed by macroeconomic information, bank-specific adversarial data, or rumors?
Crucially, the LLMs permit us to do greater than easy key phrase matching. Nineteenth-century newspaper prose is wealthy and diversified; reporters described the identical phenomena in dozens of various methods. An article may describe depositors “clamoring for his or her cash” with out ever utilizing the phrase “run.” False positives can happen when articles describe how “a ship runs right into a riverbank” or the proprietor of a financial institution “runs for workplace.” The language mannequin can perceive these descriptions in context, one thing that inflexible keyword-based approaches would miss. The LLM additionally helps us perceive whether or not the identical occasion is described in a number of articles.
To make sure excessive information high quality, we use a number of LLMs with a view to scale back probabilities of incorrect outcomes and pay particular consideration to circumstances wherein completely different fashions present completely different reply to our questions posed above. We additional validate our LLM classifications in opposition to hand-coded samples and discover excessive settlement, giving us confidence that the automated strategy produces dependable information at scale.
The entire database is publicly out there at www.finhist.com/bank-runs, the place each episode is browsable by state, metropolis, 12 months, or financial institution sort. Every episode hyperlinks to the unique newspaper articles. Under, see two examples of how newspapers reported about financial institution runs. We invite researchers and the general public to discover the info—to learn the newspaper accounts firsthand, to hint particular person episodes, and to see what historical past, with somewhat assist from AI, can inform us in regards to the dynamics of monetary instability.
Supply: Historical Financial Data.
Notes: Left panel: Protection of Peoples Nationwide Financial institution, Middletown, Delaware, Dec. 15, 1928. Proper panel: Protection of Peoples Financial institution, Cellular, Alabama, June 10, 1927.
Financial institution Runs versus Financial institution Failures
We think about three forms of misery occasions: financial institution runs, suspensions, and failures. Completely different combos of occasions can characterize various kinds of misery episodes. As an illustration, there will be financial institution runs that contain financial institution failure and everlasting financial institution closure. There can be misery episodes with a financial institution run however no financial institution failure, distinguishing between these resolved with and with out suspension. Lastly, there will be episodes wherein a financial institution fails however there is no such thing as a file of a run. Be aware that by development a financial institution should droop earlier than or at failure. Thus, any failure will even be a suspension.
The determine under reveals a Venn diagram with counts of the three forms of misery episodes. Every statement represents an episode of financial institution misery for a specific financial institution, with the identical financial institution probably being topic to misery at completely different deadlines over the pattern interval. In the course of the 1863-1934 interval, our dataset comprises greater than 3,000 financial institution run episodes. A primary main perception from our information is that almost all of financial institution runs don’t contain failure. We discover 1,906 runs with out failure and 1,515 runs with failure. We additionally discover 13,069 episodes involving a suspension, and 10,330 episodes involving a failure. Thus, nearly all of misery episodes recorded in newspapers contain a financial institution failure.
The Intersection of Financial institution Runs, Financial institution Suspensions, and Financial institution Failures
Financial institution Runs from 1863-1935
The chart under reveals the speed of runs within the time sequence by plotting the variety of runs as a fraction of the full variety of banks in every year. We deal with nationwide banks in order that we are able to calculate charges relative to the full variety of banks. The speed of runs spikes in the course of the main crises years: 1873, 1884, 1893, 1907 (to a lesser extent), and the Nice Despair. This incidence of runs confirms outstanding narratives of crises within the pre-FDIC period (e.g., Calomiris and Gorton, 1991; Wicker, 1996, 2006).
Financial institution Runs With and With out Failure from 1863 via 1934
Be aware: Based mostly on a pattern of nationwide banks.
The chart additionally distinguishes between financial institution runs with and with out failure. Runs with out failure are particularly pronounced throughout main banking crises, particularly in the course of the panics of the nationwide banking period. For instance, the Panic of 1893 featured a very giant variety of runs with out failure (however with non permanent suspensions). Runs with failure spiked in the course of the Panic of 1893 and the Nice Despair.
The Geography of Financial institution Runs
The animated map under reveals how financial institution runs ripple throughout the nation over time. Every episode seems as a glowing dot at its geographic location on its recorded date, fading over the course of the next 12 months.
The dynamics of financial institution runs from 1863 via 1934 illustrate a number of patterns instantly. First, the geographic heart of gravity of financial institution misery shifts over the a long time. Early episodes are concentrated alongside the Japanese Seaboard: New York, Philadelphia, and the main business cities. Because the nation expands westward, so does banking misery. By the Nineties, runs are showing within the Nice Plains, the Mountain West, and the Pacific Coast, reflecting the enlargement of the banking system into new agricultural and mining frontiers.
Second, the systemic crises present up as nationwide waves. In the course of the Panic of 1873, as an illustration, dots first cluster in New York Metropolis, the epicenter of the monetary system, after which radiate outward to Chicago, St. Louis, New Orleans, and smaller cities throughout the inside. The 1893 disaster, in distinction to the opposite panics of the Nationwide Banking Period, originated within the inside and noticed extra runs within the West and South, in step with misery in railroads, silver mines, and agriculture in that panic. In 1907, the disaster once more begins in New York however spreads quickly via the nationwide correspondent banking community.
Third, the map reveals the regional character of many episodes that don’t rise to the extent of a nationwide panic. The U.S. banking system of the time contained hundreds of small, under-diversified banks. Native financial downturns, crop failures, or publicity to commodity value declines might generate financial institution runs and failures with out essentially exhibiting up within the nationwide narrative. The Twenties, usually remembered as a decade of prosperity, are marked on the map by a gentle stream of financial institution failures within the agricultural Midwest and South, foreshadowing the surge in financial institution failures in the course of the Nice Despair.
What Comes Subsequent
This new database on financial institution runs opens the door to answering a variety of questions that have been beforehand troublesome to check. In our companion publish, we present how we use the info to analyze when and why runs have traditionally led to financial institution failure, and focus on how these insights have an effect on coverage discussions.
Sergio Correia is a senior economist on the Federal Reserve Financial institution of Richmond.
Stephan Luck is a monetary analysis advisor within the Federal Reserve Financial institution of New York’s Analysis and Statistics Group.
Emil Verner is the Lemelson Professor of Administration and Monetary Economics and a professor of finance at MIT Sloan Faculty of Administration.
How you can cite this publish:
Sergio Correia, Stephan Luck, and Emil Verner, “Utilizing AI to Let Historical past Communicate About Financial institution Runs,” Federal Reserve Financial institution of New York Liberty Road Economics, July 7, 2026, https://doi.org/10.59576/lse.20260707a
BibTeX: View |
operate _toggle_bibtex7(){
let el = doc.getElementById(‘bibtex7’);
el.fashion.show = el.fashion.show === ‘none’ ? ” : ‘none’;
}
@article{CorreiaLuckVerner2026,
creator={Correia, Sergio and Luck, Stephan and Verner, Emil},
title={Utilizing AI to Let Historical past Communicate About Financial institution Runs},
journal={Liberty Road Economics},
notice={Liberty Road Economics Weblog},
quantity={July 7},
12 months={2026},
url={https://doi.org/10.59576/lse.20260707a}
}
What Do Over 3,000 Financial institution Runs Educate Us About Banking Crises?
Why Do Banks Fail? Financial institution Runs Versus Solvency
Why Do Banks Fail? Three Details About Failing Banks
Disclaimer
The views expressed on this publish are these of the creator(s) and don’t essentially replicate the place of the Federal Reserve Financial institution of New York or the Federal Reserve System. Any errors or omissions are the duty of the creator(s).
