Jack Strauss
Each week, Daniels is featuring a researcher who conducts meaningful research that impacts their field and the wider community. Learn more about their work in Q&As with the Daniels Research team and email them to nominate yourself or a colleague for a future Q&A.
Jack Strauss is the Miller Chair of Applied Economics at the Daniels College of Business. Strauss has a BA in Economics from Johns Hopkins University and a PhD from Duke University. He has been a Fulbright Scholar of Economics in Kiev, Ukraine, and consulted for the Central Banks of Ukraine, Azerbaijan, Egypt, Nepal and Indonesia. He has published in the top journals of forecasting, finance and international economics, and has highly cited papers in forecasting stock returns, housing prices and job growth. Strauss has one of the most read papers in the Review of Financial Studies on stock returns, and has also published in the Journal of Finance, Review of Finance, Journal of Portfolio Management, Journal of Forecasting, International Journal of Forecasting, Journal of Applied Econometrics, Econometric Reviews, Journal of Macroeconomics as well as a more than a dozen other academic journals.
What is your area of research, and how did you become interested in it?
I specialize in forecasting, particularly in economics and finance. My work has examined employment growth, housing prices, exchange rate volatility, stock market volatility and stock returns. Recently, I’ve been focusing on forecasting stock returns using advanced econometric techniques, combination forecasts and machine learning. My interest in this area grew from experiences working in countries like Ukraine, Azerbaijan, Egypt, Indonesia, and Nepal—places known for financial instability and structural change. Those contexts taught me that traditional models break down over time, and we need methods that allow economic relationships to evolve.
Can you tell us more about your methodology?
I’m a big believer in the idea that “all models are wrong, but some are useful.” Because economic relationships shift, relying on a single model is risky. Instead, I use combination forecasting, which aggregates multiple models—an approach also known as ensemble forecasting. This methodology, which originated in weather prediction, increases accuracy by diversifying across models. In finance, it works much like portfolio diversification: spreading risk and improving stability.
How do you bring these ideas into the classroom?
With PhD students, I focus on econometric modeling and help them think critically about how data can challenge theoretical assumptions. I encourage them to try multiple approaches so the data can “speak.” For MBA and master’s students, I teach broader concepts of structural change and instability. For example, in team projects, students analyze supply and demand shocks affecting a chosen company and consider how businesses must pivot in the face of shifting relationships.
How has your research created impact outside the university?
I’ve worked as an economic consultant for the Ministry of Finance of Ukraine, the Central Banks of Azerbaijan and Egypt, and central banks in Nepal and Indonesia. In these roles, I’ve helped policymakers recognize the importance of allowing their models to adapt over time—especially in inflation forecasting. For example, in Indonesia, I trained central bankers on how to incorporate structural change into their economic models, improving their ability to forecast inflation more accurately.
What are you working on now?
I’m currently collaborating with colleagues on research into forecasting firm cash flow, R&D, patents and intangible investments. Traditional data sets undercount intangibles like patents and brand value, but we’re testing multiple definitions and showing that combining them produces more informative and accurate forecasts. It’s another example of how using multiple perspectives improves predictive power.