he electronic exchange of business to business information (e.g. purchase orders, inventory data and shipment notices between departments or organizations) can eliminate the need for human intervention and paper copy trails. Incor- porating Electronic Data Interchange (EDI) standards into an organization can drastically improve the efficiency of processing times. Modelling the behaviour of EDI messages within a Supply Chain network’s queuing system has many purposes, from understanding the efficiency of queue behaviour to process re- engineering. In this paper we demonstrate that these messages are heterogeneous, suffer from correlation, are not stationary and are challenging to model. We investigate whether a parametric or non-parametric approach is appropriate to model message service and inter-arrival times. Our results show that parametric distribution models are suitable for modelling the distribution’s tail, whilst non-parametric Kernel Density Estimation models are better suited for modelling the head.