Modelling Audit Risk Assessments: Exploration of an Alternative to the Use of Knowledge‐based Systems

Abstract

Artificial intelligence-based decision models are employed on an extensive and growing basis in audit practice and research. They facilitate the training of new practitioners, enable the more efficient use of skilled practitioners' time and provide documented consistency in decisionmaking. For these reasons the use of knowledgebased models to support decisions such as audit risk assessment has grown. This paper investigates one risk assessment decision, audit risk assessment in the purchases, inventory and accounts payable transaction cycle, which has previously been the subject of This paper compares decision-modelling approaches. The decision modelled is the assessment of inherent and control risk in the purchases, accounts payable and inventory cycle. It is modelled using two different approaches. Firstly, knowledge-based models are constructed using established development shells. Secondly, a model is constructed using a conventional procedural programming language. Both modelling approaches are tested against the output of human practitioners and compared to each other to determine if the more restrictive, assumption-laden approach offered by the procedural model is adequate to deal with the decision problem under examination, or if the greater flexibility offered by the knowledge-based approach is required. This comparison yields positive results. The procedural model is able to reproduce satisfactorily the output of the human decision makers and the knowledge-based models for the chosen decision problem. This result emphasises the importance of devoting time to the selection of the most appropriate modelling approach for a given decision problem.knowledge-based modelling, to see if it can be adequately addressed by a more restricted decision model, embodied in a purpose written procedural application. This study is a comparison of decision output of decision models constructed using these two approaches. Such a comparison can act as a trigger, signalling the need to further evaluate decision-modelling techniques before a final choice is made.The knowledge base required to construct these decision models is obtained from a case study based instrument. Two knowledge-based models were constructed to provide a comparator for the output of the procedural model. These use a rulebased knowledge representation technique, and embody the appropriate meta-knowledge to apply those rules. The procedural model incorporates the contents of these rules as a set of data items that are applied on the basis of a generalised approximation of that meta-knowledge. This approximation is inherently less flexible and, if it produces an adequate model, must thus result in a more parsimonious model of the risk assessment process.The success of the procedural model is judged by comparison of its decision output with that of the two knowledge-based models. To ensure that this comparison is meaningful, the output of all three models is also compared to that of human decision makers. Decision output for these comparisons is generated fr...