Niek Tax

Predictive Business Process Monitoring with LSTM Neural Networks

Predictive business process monitoring methods exploit logs of completed cases of a process in order to make predictions about running cases thereof. Existing methods in this space are tailor-made for specific prediction tasks. Moreover, their relative accuracy is highly sensitive to the dataset at hand, thus requiring users to engage in trial-and-error and tuning when applying them in a specific setting. This paper investigates Long Short-Term Memory (LSTM) neural networks as an approach to build consistently accurate models for a wide range of predictive process monitoring tasks. First, we show that LSTMs outperform existing techniques to predict the next event of a running case and its timestamp. Next, we show how to use models for predicting the next task in order to predict the full continuation of a running case. Finally, we apply the same approach to predict the remaining time, and show that this approach outperforms existing tailor-made methods.

A cross-benchmark comparison of 87 learning to rank methods

Learning to rank is an increasingly important scientific field that comprises the use of machine learning for the ranking task. New learning to rank methods are generally evaluated on benchmark test collections. However, comparison of learning to rank methods based on evaluation results is hindered by the absence of a standard set of evaluation benchmark collections. In this paper we propose a way to compare learning to rank methods based on a sparse set of evaluation results on a set of benchmark datasets. Our comparison methodology consists of two components: (1) Normalized Winning Number, which gives insight in the ranking accuracy of the learning to rank method, and (2) Ideal Winning Number, which gives insight in the degree of certainty concerning its ranking accuracy. Evaluation results of 87 learning to rank methods on 20 well-known benchmark datasets are collected through a structured literature search. ListNet, SmoothRank, FenchelRank, FSMRank, LRUF and LARF are Pareto optimal learning to rank methods in the Normalized Winning Number and Ideal Winning Number dimensions, listed in increasing order of Normalized Winning Number and decreasing order of Ideal Winning Number.

Heuristic approaches for generating Local Process Models through log projections

Local Process Model (LPM) discovery is focused on the mining of a set of process models where each model describes the behavior represented in the event log only partially, i.e. subsets of possible events are taken into account to create socalled local process models. Often such smaller models provide valuable insights into the behavior of the process, especially when no adequate and comprehensible single overall process model exists that is able to describe the traces of the process from start to end. The practical application of LPM discovery is however hindered by computational issues in the case of logs with many activities (problems may already occur when there are more than 17 unique activities). In this paper, we explore three heuristics to discover subsets of activities that lead to useful log projections with the goal of speeding up LPM discovery considerably while still finding high-quality LPMs. We found that a Markov clustering approach to create projection sets results in the largest improvement of execution time, with discovered LPMs still being better than with the use of randomly generated activity sets of the same size. Another heuristic, based on log entropy, yields a more moderate speedup, but enables the discovery of higher quality LPMs. The third heuristic, based on the relative information gain, shows unstable performance: for some data sets the speedup and LPM quality are higher than with the log entropy based method, while for other data sets there is no speedup at all.

Mining local process models

In this paper we describe a method to discover frequent behavioral patterns in event logs. We express these patterns as \emph{local process models}. Local process model mining can be positioned in-between process discovery and episode / sequential pattern mining. The technique presented in this paper is able to learn behavioral patterns involving sequential composition, concurrency, choice and loop, like in process mining. However, we do not look at start-to-end models, which distinguishes our approach from process discovery and creates a link to episode / sequential pattern mining. We propose an incremental procedure for building local process models capturing frequent patterns based on so-called process trees. We propose five quality dimensions and corresponding metrics for local process models, given an event log. We show monotonicity properties for some quality dimensions, enabling a speedup of local process model discovery through pruning. We demonstrate through a real life case study that mining local patterns allows us to get insights in processes where regular start-to-end process discovery techniques are only able to learn unstructured, flower-like, models.

Event Abstraction for Process Mining Using Supervised Learning Techniques

Process mining techniques focus on extracting insight in processes from event logs. In many cases, events recorded in the event log are too fine-grained, causing process discovery algorithms to discover incomprehensible process models or process models that are not representative of the event log. We show that when process discovery algorithms are only able to discover an unrepresentative process model from a low-level event log, structure in the process can in some cases still be discovered by first abstracting the event log to a higher level of granularity. This gives rise to the challenge to bridge the gap between an original low-level event log and a desired high-level perspective on this log, such that a more structured or more comprehensible process model can be discovered. We show that supervised learning can be leveraged for the event abstraction task when annotations with high-level interpretations of the low-level events are available for a subset of the sequences (i.e., traces). We present a method to generate feature vector representations of events based on XES extensions, and describe an approach to abstract events in an event log with Condition Random Fields using these event features. Furthermore, we propose a sequence-focused metric to evaluate supervised event abstraction results that fits closely to the tasks of process discovery and conformance checking. We conclude this paper by demonstrating the usefulness of supervised event abstraction for obtaining more structured and/or more comprehensible process models using both real life event data and synthetic event data.

The imprecisions of precision measures in process mining

Abstract In process mining, precision measures are used to quantify how much a process model overapproximates the behavior seen in an event log. Although several measures have been proposed throughout the years, no research has been done to validate whether these measures achieve the intended aim of quantifying over-approximation in a consistent way for all models and logs. This paper fills this gap by postulating a number of axioms for quantifying precision consistently for any log and any model. Further, we show through counter-examples that none of the existing measures consistently quantifies precision.

Mining process model descriptions of daily life through event abstraction

Methods from the area of Process Mining traditionally focus on extracting insight in business processes from event logs. In this paper we explore the potential of Process Mining to provide valuable insights in (un)healthy habits and to contribute to ambient assisted living solutions when applied on data from smart home environments. Events in smart home environments are recorded at the level of sensor triggers, which is too low to mine habit-related behavioral patterns. Process discovery algorithms produce then overgeneralizing process models that allow for too much behavior and that are difficult to interpret for human experts. We show that abstracting the events to a higher-level interpretation can enable discovery of more precise and more comprehensible models. We present a framework to automatically abstract sensor-level events to their interpretation at the human activity level. Our framework is based on the XES IEEE standard for event logs. We use supervised learning techniques to train it on training data for which both the sensor and human activity events are known. We demonstrate our abstraction framework on three real-life smart home event logs and show that the process models that can be discovered after abstraction improve on precision as well as on F-score.

Discovering more precise process models from event logs by filtering out chaotic activities

Process Discovery is concerned with the automatic generation of a process model that describes a business process from execution data of that business process. Real life event logs can contain chaotic activities. These activities are independent of the state of the process and can, therefore, happen at rather arbitrary points in time. We show that the presence of such chaotic activities in an event log heavily impacts the quality of the process models that can be discovered with process discovery techniques. The current modus operandi for filtering activities from event logs is to simply filter out infrequent activities. We show that frequency-based filtering of activities does not solve the problems that are caused by chaotic activities. Moreover, we propose a novel technique to filter out chaotic activities from event logs. We evaluate this technique on a collection of seventeen real-life event logs that originate from both the business process management domain and the smart home environment domain. As demonstrated, the developed activity filtering methods enable the discovery of process models that are more behaviorally specific compared to process models that are discovered using standard frequency-based filtering.

Log-based Evaluation of Label Splits for Process Models

Process mining techniques aim to extract insights in processes from event logs. One of the challenges in process mining is identifying interesting and meaningful event labels that contribute to a better understanding of the process. Our application area is mining data from smart homes for elderly, where the ultimate goal is to signal deviations from usual behavior and provide timely recommendations in order to extend the period of independent living. Extracting individual process models showing user behavior is an important instrument in achieving this goal. However, the interpretation of sensor data at an appropriate abstraction level is not straightforward. For example, a motion sensor in a bedroom can be triggered by tossing and turning in bed or by getting up. We try to derive the actual activity depending on the context (time, previous events, etc.). In this paper we introduce the notion of label refinements, which links more abstract event descriptions with their more refined counterparts. We present a statistical evaluation method to determine the usefulness of a label refinement for a given event log from a process perspective. Based on data from smart homes, we show how our statistical evaluation method for label refinements can be used in practice. Our method was able to select two label refinements out of a set of candidate label refinements that both had a positive effect on model precision.

Alarm-Based Prescriptive Process Monitoring

Predictive process monitoring is concerned with the analysis of events produced during the execution of a process in order to predict the future state of ongoing cases thereof. Existing techniques in this field are able to predict, at each step of a case, the likelihood that the case will end up in an undesired outcome. These techniques, however, do not take into account what process workers may do with the generated predictions in order to decrease the likelihood of undesired outcomes. This paper proposes a framework for prescriptive process monitoring, which extends predictive process monitoring approaches with the concepts of alarms, interventions, compensations, and mitigation effects. The framework incorporates a parameterized cost model to assess the cost-benefit tradeoffs of applying prescriptive process monitoring in a given setting. The paper also outlines an approach to optimize the generation of alarms given a dataset and a set of cost model parameters. The proposed approach is empirically evaluated using a range of real-life event logs.