Assessing the weighted sum algorithm for automatic generation of Probabilities in Bayesian Networks

A Bayesian Network (BN) is a probabilistic reasoning technique, which to date has been used in a broad range of applications. One of the key challenges in constructing a BN is obtaining its Conditional Probability Tables (CPTs). CPTs can be learnt from data (when available), elicited from domain experts, or a combination of both. Eliciting from domain experts provides more flexibility; however, CPTs grow in size of exponentially, thus making their elicitation process very time consuming and costly. Previous work proposed a solution to this problem using the weighted sum algorithm (WSA) [9); however no empirical results were given on the algorithm's elicitation reduction and prediction accuracy. Hence the aim of this paper is to present two empirical studies that assess the WSA's efficiency and prediction accuracy. Our results show that the estimates obtained using the WSA were highly accurate and make significant reductions in elicitation.

[1]  Richard E. Neapolitan,et al.  Chapter 4 – Learning Bayesian Networks , 2007 .

[2]  Emilia Mendes,et al.  Bayesian Network Models for Web Effort Prediction: A Comparative Study , 2008, IEEE Transactions on Software Engineering.

[3]  Balaram Das,et al.  Generating Conditional Probabilities for Bayesian Networks: Easing the Knowledge Acquisition Problem , 2004, ArXiv.

[4]  Wang Shuo,et al.  Using Expert's Knowledge to Build Bayesian Networks , 2007, 2007 International Conference on Computational Intelligence and Security Workshops (CISW 2007).

[5]  Brenda McCabe,et al.  Developing Complete Conditional Probability Tables from Fractional Data for Bayesian Belief Networks , 2007 .

[6]  Daniel Kahneman,et al.  Judgment under uncertainty: Availability: A heuristic for judging frequency and probability , 1982 .

[7]  B. Marcot,et al.  Bayesian belief networks: applications in ecology and natural resource management , 2006 .

[8]  David Heckerman,et al.  Causal independence for probability assessment and inference using Bayesian networks , 1996, IEEE Trans. Syst. Man Cybern. Part A.

[9]  Marek J. Druzdzel,et al.  An Empirical Study of Probability Elicitation Under Noisy-OR Assumption , 2004, FLAIRS.

[10]  Emilia Mendes.  The Use of Bayesian Networks for Web Effort Estimation: Further Investigation , 2008, 2008 Eighth International Conference on Web Engineering.

[11]  Kevin B. Korb,et al.  Parameterising Bayesian Networks , 2004, Australian Conference on Artificial Intelligence.

[12]  A. Tversky,et al.  Judgment under uncertainty: Judgment under uncertainty: Heuristics and biases , 1982 .

[13]  Emilia Mendes,et al.  Building an Expert-based Web Effort Estimation Model using Bayesian Networks , 2009, EASE.