Abstract: A method of anomaly detection applicable to telecommunications or retail fraud or software vulnerabilities uses inductive logic programming to develop anomaly characterization rules from relevant background knowledge and a training data set, which includes positive anomaly samples of data covered by rules. Data samples include 1 or 0 indicating association or otherwise with anomalies. An anomaly is detected by a rule having condition set which the anomaly fu,lfils. Rules are developed by addition of conditions and unification of variables, and are filtered to remove duplicates, equivalents, symmetric rules and unnecessary conditions. Overfitting of noisy data is avoided by an encoding cost criterion. Termination of rule construction involves criteria of rule length, absence of negative examples, rule significance and accuracy, and absence of recent refinement.

Abstract: The invention relates to a method of multiple criteria decision making. In particular, a method of maintaining a complex article is described that includes the steps of; (a) taking a set of options for replacing each of a plurality of components of the complex article, (b) identifying an optimum solution set from the set of possible replacement options of step (a) that best satisfies a plurality of criteria and (c) implementing an optimum solution of the optimum solution set. The step of identifying an optimum solution set comprises the step of evaluating a plurality of potential solutions from the set of possible options defined in step (a) against the plurality of criteria.