Journal of Machine Learning and Applications

Bayesian Network

---

A Bayesian network (BN) is a probabilistic graphical model describing information about an uncertain domain where each node relates to a random variable, and each edge reflects the conditional probability for the relevant random variables. It is also known as a Bayesian model, Bayes network, belief network, or decision network. Bayesian networks are excellent at analyzing an event that has already happened and determining the likelihood that any one of multiple potential known causes was a contributing element. Bayesian networks employ probability theory for prediction and anomaly detection and are created from a probability distribution, making them probabilistic. These networks can be used for a wide range of applications, including forecasting, detecting anomalies, diagnosing, automated insight, reasoning, predicting time series, and making decisions in the face of ambiguity.