Whitepaper Sheds Light on Predicting the Future
February 16, 2013
A new white paper from Microsoft Research indicates that search is now future-oriented. The detailed paper, “Mining the Web to Predict Future Events” (PDF) was composed by Kira Radinsky of the Technion-Israel Institute of Technology and Microsoft Research’s Eric Horvitz. The introductory Abstract specifies:
“We describe and evaluate methods for learning to forecast forthcoming events of interest from a corpus containing 22 years of news stories. We consider the examples of identifying significant increases in the likelihood of disease outbreaks, deaths, and riots in advance of the occurrence of these events in the world. We provide details of methods and studies, including the automated extraction and generalization of sequences of events from news, corporate, and multiple web resources. We evaluate the predictive power of the approach on real-world events withheld from the system.”
The researchers delve into the management of large amounts of information from a variety of sources (including bits of news that may seem insignificant at first) and patterns that can be extracted from such data. They illustrate their points with a series of evaluations and representative examples, and conclude that automated analysis can, indeed, discover helpful new relationships and context-sensitive outcome probabilities.
Radinsky and Horvitz conclude with the hope that other researchers will take up this topic, and that such research will lead to “valuable predictions about future events and interventions of importance.” See the paper for the thorough details behind this optimistic stance.
Cynthia Murrell, February 16, 2013