Process Model Forecasting Using Time Series Analysis of Event Sequence Data

Process analytics is an umbrella of data-driven techniques which includes making predictions for individual process instances or overall models. At the instance level, various novel have been recently devised, tackling next activity, remaining time, and outcome prediction. model there a notable void. It ambition this paper to fill gap. To end, we develop technique forecast entire from historical event data. A forecasted will-be representing probable future state process. Such helps investigate consequences drift emerging bottlenecks. Our builds on representation data as multiple time series, each capturing evolution behavioural aspect model, such that corresponding forecasting can be applied. implementation demonstrates accuracy our real-world log