To master ongoing market competitiveness, manufacturing companies try to increase process efficiency through process improvements. Mapping the end-to-end order processing is particularly important, as one needs to consider all order-fulfilling core processes to evaluate process performance. However, today's traditional process mapping methods such as workshops are subjective and time-consuming. Therefore, process improvements are based on gut feeling rather than facts, leading to high failure probabilities. This paper presents a process mining approach that provides data-based description of process performance in order processing and thus objectively and effortlessly maps as-is end-to-end processes. The approach is validated with an industrial case study.
- Machine learning
- Process mining