While daily business news reports on financial markets, research says it can also offer insights into their future direction.
A recent study by University of Auckland finance lecturer Dr. Justin J. Case and Queensland University of Technology’s Professor Adam Clements demonstrates that analysing business news articles, particularly those from The Wall Street Journal, provides more accurate forecasts of stock market volatility than traditional methods.
The study used more than 1.1 million Wall Street Journal articles published from January 2000 to December 2022, examining the language used in business reporting and connecting it to movements in the S&P 500, the world’s most closely followed stock market index.
“We’re looking at the world’s biggest equities market and the biggest business newspaper in the US and asking whether the news explains stock market volatility,” Case said.
The researchers used a machine learning algorithm to categorise the news articles by topic and analysed this information in conjunction with high-frequency data from the S&P 500 index.
“We find that news coverage is strongly related to stock market volatility movements. And by analysing business news articles, we can identify both the topics and specific events influencing stock market volatility,” Case added.
The researchers discovered that integrating their news-based metrics into standard volatility forecasting models lowered forecast errors by more than 40% over a monthly timeframe.
They also observed decreases in forecast errors at weekly intervals.
“If you’re able to forecast volatility more accurately with our news measures, you can decrease your risk exposure and, therefore, increase your portfolio performance,” Case said.
Moreover, news topics on stock market activity, financial institutions, economic shocks, and government policy showed the strongest connections to stock market volatility.
“Interestingly, we also identify several news topics associated with a less volatile stock market. In particular, news attention to corporate mergers and acquisitions is associated with reduced volatility. This suggests that increased mergers and acquisitions news coincides with greater confidence in economic conditions.”
The researchers also investigated whether the large language model, ChatGPT, can predict the impact of news on market volatility. The study concludes that the model’s forecasting accuracy is weaker than the researchers’ method over longer time horizons.