Financial publications offer a range of metrics for tracking the economy. But can they help analysts predict events like a recession?
Researchers at Yale tried to
answer this question. They ran software to scour hundreds of thousands of Wall Street Journal stories and quantify the attention paid to certain topics.
Specifically, they
wanted to know whether “recession” news was linked to changes of production and employment over a three-year period.
“We have a data problem,” said Leland Bybee,
a PhD student in financial economics at Yale SOM, according to an article in Yale insights. “It’s very difficult to get really good, high-quality data to understand what
is going on in the economy at any given point in time.”
The authors gathered roughly 763,000 WSJ articles, published from 1984 to 2017. The software counted
the number of times that specific one- or two-word terms were used in each article, then a machine-learning algorithm identified broad topics—i.e., clusters of terms that often appeared
together, the article continues. They then did a manual review.
advertisement
advertisement
One set of words that popped up included “Greenspan,” “Yellen,” “federal-funds rate”
and “raise rate,” etc. The software identified the topic as the Federal Researve.
The result of this exercise? The team found that “an increase in the
‘recession’ attention measure, from the 5th to the 95th percentile, was correlated to a 1.99% drop in industrial production 17 months later and a 0.92% drop in employment 20 months
later.”
In other words, the recession attention metric appeared to provide additional forecasting ability.
Moreover, “news attention to topics such as
‘recession’ and ‘problems’ (a general category that included terms such as ‘big problem,’ ‘major problem,’ ‘mess,’ ‘debacle,’
and so on) could explain 25% of the variation in stock market returns. In contrast, a set of 101 other economic measures could explain only 9%."
The research team included
Bybee and Bryan T. Kelly, professor of Finance & Associate Director, International Center for Finance. The article was written by Roberta Kwok.