“It is exceedingly difficult to make predictions, particularly about the future.”

This quip has been attributed to Niels Bohr, Yogi Berra, Samuel Goldwyn, and Albert Einstein. Regardless of who coined it, says SFI VP Chris Wood, it nicely captures the focus of a recent SFI Business Network Topical Meeting, “Forecasting in the Face of Uncertainty and Risk,” hosted by Morgan Stanley in New York.

The October meeting brought together scientists, economists, and representatives of the financial industry to explore, from a multidisciplinary perspective, the problem of forecasting.

Chris, who directs the Business Network, co-organized the event with Marty Liebowitz of Morgan Stanley, Michael Mauboussin of Legg Mason Capital Management (an SFI Trustee), and SFI External Professor John Rundle of UC Davis. It included presentations on the accomplishments and challenges of forecasting from experts in the physical sciences, economics, the financial services industry, even sports and politics.

Susan Avery, President of the Woods Hole Oceanographic Institution, discussed forecasting of atmospheric-oceanic events, including the recent Hurricane Irene. U.S. Geological Survey Director Marcia McNutt reviewed the challenges of forecasting the nonlinear effects of climate change. Rundle discussed how the heavy-tailed statistics that describe earthquake frequency and magnitude can be applied to financial markets.

Ole Peters, a former SFI postdoctoral fellow now at Imperial College, described how an approach based on ensemble averaging that has dominated economic forecasting for nearly a century is based on an erroneous conclusion about an equation published in 1934. Careful attention to the appropriate time averages can better account for the risk inherent in financial markets, he said.

Financial experts Henry Kauffman, Rick Bookstaber, and Bill Miller participated in a concluding panel discussion moderated by co-organizer Liebowitz about financial forecasting and the importance of “outside-the-box” perspectives.

“There is great value in bringing together people who attempt to address the common problem of forecasting from different perspectives and based on very different kinds of data,” says Chris.