PROBABILISTIC INFERENCE IN BAYESIAN INSURANCE NETWORK
Yana Bondarenko, D. O. Rachko, A. O. Rozlyvan · Problems of applied mathematics and mathematic modeling · 2020
In this paper, the technique to solve the prediction problem of reparation of the financial losses caused by a road traffic accident is solved. Exact inference is represented using the Sum-Product Variable Elimination algorithm, Sum-Product Variable Elimination algorithm for computing conditional probabilities, Max-Product Variable Elimination algorithm for MAP, Max-Sum-Product Variable Elimination algorithm for marginal MAP. Reasoning patterns are presented graphically and descriptively.