EMBERS at 4 years: Experiences operating an Open Source Indicators Forecasting System
Computers and Society
2016-04-04 v1 Social and Information Networks
Abstract
EMBERS is an anticipatory intelligence system forecasting population-level events in multiple countries of Latin America. A deployed system from 2012, EMBERS has been generating alerts 24x7 by ingesting a broad range of data sources including news, blogs, tweets, machine coded events, currency rates, and food prices. In this paper, we describe our experiences operating EMBERS continuously for nearly 4 years, with specific attention to the discoveries it has enabled, correct as well as missed forecasts, and lessons learnt from participating in a forecasting tournament including our perspectives on the limits of forecasting and ethical considerations.
Cite
@article{arxiv.1604.00033,
title = {EMBERS at 4 years: Experiences operating an Open Source Indicators Forecasting System},
author = {Sathappan Muthiah and Patrick Butler and Rupinder Paul Khandpur and Parang Saraf and Nathan Self and Alla Rozovskaya and Liang Zhao and Jose Cadena and Chang-Tien Lu and Anil Vullikanti and Achla Marathe and Kristen Summers and Graham Katz and Andy Doyle and Jaime Arredondo and Dipak K. Gupta and David Mares and Naren Ramakrishnan},
journal= {arXiv preprint arXiv:1604.00033},
year = {2016}
}
Comments
Submitted to a conference