Large Language Models Can Improve Stock Market Forecasts
Analyzing both numbers and narrative context in company reports led to better price forecasts.
Large Language Models Can Improve Stock Market ForecastsGlen Gyssler
Cryptocurrencies are famous for exposing investors to wild price changes. Bitcoin, for example, appreciated more than 70 percent during the first quarter of 2021, but on May 19 of that year, dropped by 30 percent in the course of the day before recovering some of its value. Do such dramatic climbs and falls reflect changes in fundamental information about crypto assets? Or are they driven by investor sentiment? And as cryptocurrencies become more salient to the financial system, does their price volatility pose a risk to broader financial stability? To explore these questions, Chicago Booth’s Initiative on Global Markets polled its US and European experts panels on the roots and possible consequences of crypto’s ups and downs.
Judith Chevalier, Yale
“I would also have agreed if the question asked about the value of gold bullion.”
Response: Agree
Darrell Duffie, Stanford
“Despite use cases such as remittances
and illegal payments, total dollar volatility seems out of proportion to the value of
such services.”
Response: Strongly agree
Christian Leuz, Chicago Booth
“Clearly speculation drives much of the volatility, but there’s also evidence that hashrate, network size, or more traditional pricing factors matter.”
Response: Uncertain
Jan Pieter Krahnen, Goethe University Frankfurt
“There is a rising risk of contagion into
the regulated banking sector if crypto
assets become part of the asset universe held by banks.”
Response: Agree
Lubos Pastor, Chicago Booth
“Perhaps one day, but today we are still very far from such a situation. Moreover, regulation is already happening, at least
in Europe.”
Response: Disagree
Richard Schmalensee, MIT
“If they become a serious risk, one would hope that regulations would be changed.”
Response: Uncertain
Analyzing both numbers and narrative context in company reports led to better price forecasts.
Large Language Models Can Improve Stock Market ForecastsExperts in finance and economics consider the costs and benefits of the US’s contentious cap on borrowing.
Does the Debt Ceiling Do More Harm than Good?Some degree of concentration in subprime credit markets could be good for consumers.
When It Comes to Subprime Car Loans, Competition Drives Rates UpYour Privacy
We want to demonstrate our commitment to your privacy. Please review Chicago Booth's privacy notice, which provides information explaining how and why we collect particular information when you visit our website.