Basket Analysis

Abstract

A basket is a set of items purchased together (for example, in a supermarket). Basket analysis is finding items frequently occurring in the same basket. Such dependencies between items are represented by association rules. Bayes' rule One of the pillars of probability theory where for two or more random variables that are not independent, we write conditional probability in one direction in terms of the conditional probability in the other direction: P(B|A) = P(A|B)P(B)/P(A). It is used, for example, in diagnosis where we are given P(A|B) and B is the cause of A. Calculating P(B|A) allows a diagnostics-that is, the calculation of the probability of the cause B given the symptoms A. Bayesian estimation A method for parameter estimation where we use not only the sample, but also the prior information about the unknown parameters given by a prior distribution. This is combined with the information in the data to calculate a posterior distribution using Bayes' rule. Bayesian network See graphical model. Bioinformatics Computational methods, including those that use machine learning, for analyzing and processing biological data. Biometrics Recognition or authentication of people using their physiological characteristics (for example, face, fingerprint) and behavioral characteristics (for example, signature, gait).