Universality and prediction in business rules

Abstract

Business rules (BR) have the form ⟨if condition then action⟩. A BR program, which can be executed by means of an interpreter, is a sequence of business rules. Motivated by International Business Machines use cases, we look at the problem of setting parameter values in a given BR program so it will achieve a given average goal over all possible instances. We explore the following fundamental question: Is there a general learning algorithm, which addresses this issue? We prove the answer is negative. On the positive side, we derive operational semantics for BR programs. As a proof of concept, we show empirically that these can be used to detect potential nontermination situations.