Wisdom of the Crowd? Building Better Forecasts from Suboptimal Predictors

Research

Find Labs
View list of research
Departments and Research Centers
Interdisciplinary Group Research
List of Emeritus Professors

View list of research

Scientists at the University of Tokyo and Kozo Keikaku Engineering Inc. have shown how to combine the forecasts of a collection of suboptimal "delay embedding" predictors for time series data. This work may help improve the forecasting of floods, stock market gyrations, spatio-temporal brain dynamics, and ecological resource fluctuations.

2020.01.21

Press Release

Wisdom of the Crowd? Building Better Forecasts from Suboptimal Predictors

The University of Tokyo research shows how combining imperfect predictors can significantly improve the accuracy of time series forecasting, offering potential for predicting natural disasters, resource fluctuations, and financial indicators.