November 2024 Update
November 3, 2024 — October’s market activity can be neatly summarized in a single chart: the dollar (BBDXY) was strong and U.S. stocks (the VOO
U.S. vs International Stock Performance
October 14, 2024 — Over the last 20 years U.S. stocks and bonds have meaningfully outperformed their global peers, both in absolute terms, and on
October 2024 Update
October 2, 2024 — The major market event in September was the Fed’s 50 basis point rate cut following the September 18th Federal Open Market
September 2024 Update
September 2, 2024 — After a bit of an early-August swoon, the stock market came roaring back in the last few weeks of the month.
August 2024 Update
August 1, 2024 — Despite a partial reversal on the final trading day of the month, July saw a large momentum crash with past winners
July 2024 Update
July 1, 2024 — June of 2024 was a good month for financial markets. Leading the pack were (again) technology stocks, with the NASDAQ up
June 2024 Update
June 2, 2024 — After a weak April, markets bounced back in May, with the S&P 500 staging a breathtaking rally in the final few
May 2024 Update
May 3, 2024 — From the end of March until the end of April, the market had a serious rethink about the path of monetary
April 2024 Update
April 3, 2024 — As hints of spring emerged in an unseasonably warm March, markets continued to rally, with the S&P 500 up over 3%.
Academic Papers
Journal of Financial and Quantitative Analysis
Does Unusual News Forecast Market Stress?
An increase in “unusual” news with negative sentiment predicts an increase in stock market volatility. Unusual positive news forecasts lower volatility. Our analysis is based on over 360,000 articles on 50 large financial companies, published during the period of 1996–2014…
Journal of Financial Economics
Risk and returns around the world
We develop a classification methodology for the context and content of news articles to predict risk and return in stock markets in 51 developed and emerging economies. A parsimonious summary of news, including topic-specific sentiment, frequency, and unusualness (entropy) of word flow…
Proceedings of ACM International Conference on AI in Finance
Choosing News Topics to Explain Stock Market Returns
We analyze methods for selecting topics in news articles to explain stock returns. We find, through empirical and theoretical results, that supervised Latent Dirichlet Allocation (sLDA) implemented through Gibbs sampling in a stochastic EM algorithm will often overfit returns to the detriment…
Cato Journal
How Natural Language Processing Will Improve Central Bank Accountability
In the movie “True Lies,” Arnold Schwarzenegger plays the role of a skilled spy. In one scene, he is injected with truth serum in preparation for interrogation. Under the influence of the truth serum, he reveals how he plans to kill his captors and escape and then applies his skills and weapons…
Review of Asset Pricing Studies
Investor Information Choice with Macro and Micro Information
We develop a model of information and portfolio choice in which ex ante identical investors choose to specialize because of fixed attention costs required in learning about securities. Without this friction, investors would invest in all securities and would be indifferent across a wide range of information choices…
Management Science (revise/resubmit)
Dynamic Information Regimes in Financial Markets
We develop a model of investor information choices and asset prices where the availability of information about fundamentals is time-varying. A competitive research sector produces more information when more investors are willing to pay for that research…
Journal of Finance
Foundations of technical analysis
Technical analysis, also known as charting,’ has been part of financial practice for many decades, but this discipline has not received the same level of academic scrutiny and acceptance as more traditional approaches such as fundamental analysis. One of the main obstacles is the highly subjective nature of technical analysis…
Columbia Business School Working Paper
Time Variation in the News-Returns Relationship
The well-documented underreaction of stock prices to news exhibits substantial time variation. We show that higher risk-bearing capacity of financial intermediaries, lower passive ownership of stocks, and greater informativeness of news increase price responses to contemporaneous news…
Columbia Business School Working Paper
Predicting the Oil Market
We study the performance of many traditional and novel, text-based variables for in-sample and out-of-sample forecasting of oil spot, futures, and energy company stock returns, and changes in oil volatility, production, and inventories. After controlling for small-sample biases, we find evidence of in-sample predictability…
Columbia Business School Working Paper
News and Markets in the Time of COVID-19
The initial phase of the COVID-19 pandemic was characterized by voluminous, highly negative news coverage. Markets overreacted to uninformative news, and reacted more to news during high volatility periods. News coverage responded to lagged market activity, and causally impacted contemporaneous returns…