Sequential Entropy Pooling Heuristics

Abstract

This article introduces two sequential heuristics that are designed to overcome some of the practical limitations of the Entropy Pooling (EP) method. Both heuristics repeatedly apply EP to sequentially arrive at the posterior probability and usually lead to significantly better solutions than the original approach. In some cases, the sequential heuristics coincide with the original method, while they automatically ensure logical consistency in others. They are also able to solve interesting and practically relevant problems that the original approach simply cannot. Given the benefits of the sequential heuristics, this article argues that they should become the standard for future EP applications.

Documented Python code that replicates the results of the original approach is available in the open-source package fortitudo.tech. More information about the package can be found on https://os.fortitudo.tech.

Keywords: Entropy Pooling, relative entropy, Kullback-Leibler divergence, change of measure, market views, stress-tests, Monte Carlo simulation, nonlinear convex optimization, heuristic algorithms, Python Programming Language.

JEL Classification: C02, C11, C61, G1