Scalable Algorithms for Aggregating Disparate Forecasts of Probability

TL;DR

This paper introduces a scalable algorithm for aggregating large sets of incoherent probability forecasts, with strong performance guarantees and applications in risk assessment and sensor networks.

Contribution

It presents a novel, efficient algorithm for large-scale probability aggregation with proven performance bounds, applicable to real-world risk and sensor data.

Findings

Algorithm is significantly faster than existing methods.

Provides provable performance guarantees.

Uncovers connections between risk assessment and sensor networks.

Abstract

In this paper, computational aspects of the panel aggregation problem are addressed. Motivated primarily by applications of risk assessment, an algorithm is developed for aggregating large corpora of internally incoherent probability assessments. The algorithm is characterized by a provable performance guarantee, and is demonstrated to be orders of magnitude faster than existing tools when tested on several real-world data-sets. In addition, unexpected connections between research in risk assessment and wireless sensor networks are exposed, as several key ideas are illustrated to be useful in both fields.