The research area of process mining concerns itself with knowledge discovery from event logs, containing recorded traces of executions as stored by process aware information systems. Over the past decade, research in process mining has increasingly focused on predictive process monitoring to provide businesses with valuable information in order to identify violations, deviance and delays within a process execution, enabling them to carry out preventive measures. In this paper, we describe a practical case in which both exploratory and predictive process monitoring techniques were developed to understand and predict completion times of a luggage handling process at an airport. From a scientific perspective, our main contribution relates to combining a random forest regression model and a Long Short-Term Memory (LSTM) model into a novel stacked prediction model, in order to accurately predict completion time of cases.
Developing LSTM neural networks that can accurately predict the future trajectory of ongoing cases and their remaining runtime is an active area of research in predictive process monitoring. In this work a novel complete remaining trace prediction (CRTP) LSTM is proposed. This model is trained to directly predict the complete remaining trace and runtime of cases in contrast to single event prediction as is considered in previously published research on this topic. This makes the CRTP-LSTM robust in terms of utilizing all available attributes of previously observed events for prediction, consequently it can be considered natively data aware. In an extensive experimental assessment the authors show that CRTP-LSTMs consistently outperform other considered approaches for both remaining trace and runtime prediction. Furthermore, the authors show that including all available information contained in previously observed events has a positive impact on the performance of the CRTP-LSTM model. This indicates that valuable information can be extracted from attributes of events in order to make more accurate trace and runtime predictions. This opens up interesting avenues for future research including the incorporation of inter-case features into a modeling setup when predicting the remaining trace and runtime of cases.
Over the past decades, decision makers have increasingly relied on analytical methods in order to increase revenues and reduce costs. This is also the case for marketing, where predictive models have primarily been used to identify potential customers and measure the effects of marketing campaigns. In this paper, we introduce a methodology to optimally distribute a constrained marketing budget over a group of targets for which historical behavioral information is available, though where it is deemed infeasible to set up a trial campaign involving a control and test group as is the typical approach described by "net lift" modelling. Instead, so called "swing clients" are identified based on a notion of uncertainty following from any classification technique which can be trained over the historical data, which makes that our approach is easily applicable in most marketing environments. We report on the feasible of our approach by presenting a case study which was performed at the largest airport in Belgium.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.