Monday 13 April 2020

Basic training with a Bayesian network tool helps lay people solve complex problems

Researchers at UCL and Birkbeck have published an important study on the benefits of using a Bayesian Network (BN) tool to solve the kinds of complex problems that intelligence analysts are confronted with.

Example of the type of problem considered. Participants had to answer questions such as which group was most likely responsible for the attack based on various details about multiple informant sources and their accuracy

The work was part of the IARPA funded BARD (Bayesian ARgumentation via Delphi) project which developed a BN tool tailored for intelligence analysts*

The study provides strong empirical evidence that if you provide basic training to use the BARD tool for constructing BNs then this improves the ability of individuals to solve complex probabilistic reasoning problems, compared to a control group receiving only generic training in probabilistic reasoning. 

The full details of the paper (which includes a link to all of the problems and data) are:


Cruz, N., Desai, S. C., Dewitt, S., Hahn, U., Lagnado, D., Liefgreen, A., Phillips, K., Pilditch, T., and  Tešić, M. (2020). "Widening Access to Bayesian Problem Solving". Frontiers in Psychology, 11, 660. https://doi.org/10.3389/fpsyg.2020.00660

*I declare an interest here: the BARD tool was developed from the AgenaRisk API.
** Again I declare an interest: I was involved with some of the training

No comments:

Post a Comment