Gazi Fuad, a senior majoring in statistics and in mathematical economic analysis, is the author of a white paper, titled Economic Forecasting with News Headlines.
Fuad’s goal for the project was to investigate creative techniques and data sources to measure consumer sentiment more quickly and cost-effectively than using the Index of Consumer Sentiment (ICS).
“Consumer sentiment, which measures how confident individuals feel in the strength of the economy, is a crucial indicator of the overall health of the U.S. economy. However, there are costs and time delays associated with collecting the survey responses associated with the ICS,” said Fuad.
Fuad’s paper was the final element of his senior capstone project with Associate Teaching Professor Elizabeth McGuffey. Daniel Kowal, the Dobelman Family Assistant Professor of Statistics, served as his project advisor.
Fuad presented his paper on Friday, Dec. 8, 2023. The paper was subsequently selected the following week for the CoFES White Paper Series.
Fuad has a keen interest in blending knowledge of computer and data science to quantitatively understand and effectively solve a range of complex problems. He has interned for Amazon in Seattle, WA; Bliss Point Media in Santa Monica, CA; and the Federal Reserve Bank in Boston, MA.
For this project, he used natural language processing techniques such as latent Dirichlet allocation and sentiment analysis to extract quantifiable topics and sentiments from news headlines on the front page of top publications’ websites. He then used that information as predictors for the monthly personal savings and labor force participation rates. The topics and sentiments served as exogenous inputs in a Seasonal Autoregressive Integrated Moving Average with eXogenous regressors (SARIMAX) model to predict the actual rates, and as covariates in classification models to predict the direction of rate movement.
Fuad’s findings showed that topic-sentiment combinations from news headlines have considerable predictive power in modeling future economic conditions even when compared to the predictive power of the ICS.
Fuad is also an ardent photographer for the Rice Thresher, Moody Center for the Arts, and other freelance projects. Other projects and experiences have included mentoring for the Rice DataSci Club and serving as the president of Will Rice College, one of the residential colleges at Rice University.
- Shawn Hutchins, Communications and Marketing Specialist
