Abstract
Business process simulation is an effective approach to many organisations to understand the progress of processes over a period of time and predict future activities, which can then be given as a feedback to their customers and improve their overall productivity. In order to provide valuable information to both customers and system managers, the timings of business processes need to be forecast with high accuracy and efficiency. In particular, organisations require to study the process and event flows, recognize their patterns, and forecast the total time it would take for a workflow to complete. This paper proposes the architecture for business process simulation and describes its prototype implementation. It lists several prediction techniques that have been implemented as part of the prototype system. The paper also describes an artificial neural network model that could be used for predicting the completion time of business processes that are constrained by the availability of resources.