Galdo Seara, L., & De Carvalho, R. M. (2019). An approach for workflow improvement based on outcome and time remaining prediction. In S. Hammoudi, B. Selic, & L. F. Pires (Eds.), MODELSWARD 2019 – Proceedings of the 7th International Conference on Model-Driven Engineering and Software Development (pp. 475-482). Setúbal: SCITEPRESS-Science and Technology Publications, Lda.. DOI: 10.5220/0007577504750482
Some business processes are critical to organizations. The efficiency at which involved tasks are performed define the quality of the organization. Detecting where bottlenecks occur during the process and predicting when to dedicate more resources to a specific case can help to distribute the work load in a better way. In this paper we propose an approach to analyze a business process, predict the outcome of new cases and the time for its completion. The approach is based on a transition system. Two models are then developed for each state of the transition system, one to predict the outcome and another to predict the time remaining until completion. We experimented with a real life dataset from a financial department to demonstrate our approach.