This Article 
 Bibliographic References 
 Add to: 
Probability Bounds for Goal Directed Queries in Bayesian Networks
September/October 2002 (vol. 14 no. 5)
pp. 1196-1200

Abstract—We derive bounds on the probability of a goal node given a set of acquired input nodes. The bounds apply to decomposable networks; a class of Bayesian Networks encompassing causal trees and causal polytrees. The difficulty of computing the bounds depends on the characteristics of the decomposable network. For directly connected networks with binary goal nodes, tight bounds can be computed in polynomial time. For other kinds of decomposable networks, the derivation of the bounds requires solving an integer program with a nonlinear objective function, a computationally intractable problem in the worst case. We provide a relaxation technique that computes looser bounds in polynomial time for more complex decomposable networks. We briefly describe an application of the probability bounds to a record linkage problem.

[1] J.B. Copas and F.J. Hilton, “Record Linkage: Statistical Methods for Matching Computer Records,” J. Royal Statistical Soc., vol. 153, no. 3, pp. 287-320, 1990.
[2] D. Dey and V. Mookerjee, “A Sequential Technique for Efficient Record Linkage in Heterogeneous Databases,” Working Paper Series, Dept. of Management Science, Univ. of Washington, 1999.
[3] S. Dittmer and F. Jensen, “Myopic Value of Information in Influence Diagrams,” Proc. 13th Conf. Uncertainty in Artificial Intelligence, Geiger and Shenoy, eds., 1997.
[4] K. Ezawa and S. Norton, “Constructing Bayesian Networks to Predict Uncollectible Telecommunications Accounts,” IEEE Expert, vol. 11, no. 5, pp. 45-51, Oct. 1996.
[5] D. Heckerman, J. Breese, and K. Rommelse, “Troubleshooting under Uncertainty,” Comm. ACM, vol. 38, no. 3, pp. 27-41, Mar. 1995.
[6] E. Horowitz and S. Sahni, Fundamentals of Data Structures in Pascal. Rockville, Md.: Computer Science Press, 1989.
[7] F. Jensen, An Introduction to Bayesian Neworks. Springer Verlag, 1996.
[8] F. Jensen and J. Liang, “drHugin: A System for Value of Information in Bayesian Networks,” Proc. Fifth Int'l Conf. Information Processing and Management of Uncertainty in Knowledge-Based Systems (IPMU), pp. 178-183, 1994.
[9] S. Lauritzen and D. Spiegelhalter, “Local Computations with Probabilities on Graphical Structures and their Applications to Expert Systems,” J. Royal Statistical Soc. B, vol. 50, no. 2, 1988.
[10] M. Mannino and V. Mookerjee, “Optimizing Expert Systems: Heuristics for Efficiently Generating Low Cost Information Acquisition Strategies,” INFORMS J. Computing, vol. 11, no. 3, pp. 278-291, Summer 1999.
[11] M. Mannino, V. Mookerjee, and R. Gilson, “A Method For Reducing the Cost of Operating a Bayesian Network-Based Expert System,” Proc. INFORMS Conf. Information Systems and Technology, May 1997.
[12] J. Mingers, “An Empirical Comparison of Pruning Methods for Decision Tree Induction,” Machine Learning, vol. 4, no. 2, pp. 227-243, 1989.
[13] V. Mookerjee and M. Mannino, “Sequential Decision Models for Expert System Design,” IEEE Trans. Knowledge and Data Eng., vol. 9, no. 5, pp. 675-687, Sept./Oct. 1997.
[14] R. Neapolitan, Probabilistic Reasoning in Expert Systems: Theory and Algorithms, John Wiley&Sons, New York, 1990.
[15] H.B. Newcombe, Handbook of Record Linkage. Oxford University Press, 1988.
[16] J. Pearl, Probabilistic Reasoning in Intelligent Systems. San Mateo, Calif.: Morgan Kaufman, 1988.
[17] P. Shenoy, “Valuation-Based Systems for Bayesian Decision Analysis,” Operations Research, vol. 40, no. 3, pp. 463-484, 1992.

Index Terms:
Bayesian networks, probability bounds, acquisition cost, sequential decision making.
Michael V. Mannino, Vijay S. Mookerjee, "Probability Bounds for Goal Directed Queries in Bayesian Networks," IEEE Transactions on Knowledge and Data Engineering, vol. 14, no. 5, pp. 1196-1200, Sept.-Oct. 2002, doi:10.1109/TKDE.2002.1033865
Usage of this product signifies your acceptance of the Terms of Use.