Johannes De Smedt

Galina Deeva, Johannes De Smedt, Cecilia Saint-Pierre et al.

A growing number of universities worldwide use various forms of online and blended learning as part of their academic curricula. Furthermore, the recent changes caused by the COVID-19 pandemic have led to a drastic increase in importance and ubiquity of online education. Among the major advantages of e-learning is not only improving students' learning experience and widening their educational prospects, but also an opportunity to gain insights into students' learning processes with learning analytics. This study contributes to the topic of improving and understanding e-learning processes in the following ways. First, we demonstrate that accurate predictive models can be built based on sequential patterns derived from students' behavioral data, which are able to identify underperforming students early in the course. Second, we investigate the specificity-generalizability trade-off in building such predictive models by investigating whether predictive models should be built for every course individually based on course-specific sequential patterns, or across several courses based on more general behavioral patterns. Finally, we present a methodology for capturing temporal aspects in behavioral data and analyze its influence on the predictive performance of the models. The results of our improved sequence classification technique are capable to predict student performance with high levels of accuracy, reaching 90 percent for course-specific models.

Yongbo Yu, Jari Peeperkorn, Johannes De Smedt et al.

Process Model Forecasting (PMF) aims to predict how the control-flow structure of a process evolves over time by modeling the temporal dynamics of directly-follows (DF) relations, complementing predictive process monitoring that focuses on single-case prefixes. Prior benchmarks show that machine learning and deep learning models provide only modest gains over statistical baselines, mainly due to the sparsity and heterogeneity of the DF time series. We investigate Time Series Foundation Models (TSFMs), large pre-trained models for generic time series, as an alternative for PMF. Using DF time series derived from real-life event logs, we compare zero-shot use of TSFMs, without additional training, with fine-tuned variants adapted on PMF-specific data. TSFMs generally achieve lower forecasting errors (MAE and RMSE) than traditional and specialized models trained from scratch on the same logs, indicating effective transfer of temporal structure from non-process domains. While fine-tuning can further improve accuracy, the gains are often small and may disappear on smaller or more complex datasets, so zero-shot use remains a strong default. Our study highlights the generalization capability and data efficiency of TSFMs for process-related time series and, to the best of our knowledge, provides the first systematic evaluation of temporal foundation models for PMF.

Jakob De Moor, Hans Weytjens, Johannes De Smedt et al.

Prescriptive Process Monitoring (PresPM) recommends interventions during business processes to optimize key performance indicators (KPIs). In realistic settings, interventions are rarely isolated: organizations need to align sequences of interventions to jointly steer the outcome of a case. Existing PresPM approaches fall short in this respect. Many focus on a single intervention decision, while others treat multiple interventions independently, ignoring how they interact over time. Methods that do address these dependencies depend either on simulation or data augmentation to approximate the process to train a Reinforcement Learning (RL) agent, which can create a reality gap and introduce bias. We introduce SCOPE, a PresPM approach that learns aligned sequential intervention recommendations. SCOPE employs backward induction to estimate the effect of each candidate intervention action, propagating its impact from the final decision point back to the first. By leveraging causal learners, our method can utilize observational data directly, unlike methods that require constructing process approximations for reinforcement learning. Experiments on both an existing synthetic dataset and a new semi-synthetic dataset show that SCOPE consistently outperforms state-of-the-art PresPM techniques in optimizing the KPI. The novel semi-synthetic setup, based on a real-life event log, is provided as a reusable benchmark for future work on sequential PresPM.

Marco Gregnanin, Johannes De Smedt, Giorgio Gnecco et al.

Forecasting univariate time series in the financial market is a challenging endeavor. While numerous statistical and machine learning models have been introduced to address this challenge, they typically concentrate solely on analyzing temporal patterns within the time series data. In this research, we study the statistical significance of the inclusion of geometric patterns in enhancing forecasting accuracy within the context of time series analysis. We introduce the Time-Geometric model, a combination of models designed to exploit both geometric and temporal patterns. The contribution of this research lies in advancing the domain of univariate time series prediction,as demonstrated through extensive empirical evaluations. Our findings underscore that leveraging geometric patterns, captured through Graph Neural Networks, yields statistically significant improvements in forecasting accuracy.

Marco Gregnanin, Johannes De Smedt, Giorgio Gnecco et al.

Hypergraphs have the capacity to capture higher-dimensional relationships among entities across various domains, making them a subject of growing interest within the research community for understanding the structure and dynamics of complex systems. However, a key challenge is the derivation of hypergraph representations from time series data in situations where the structure of the hypergraph is limited or absent. In this study, we propose a model that constructs a dynamic hypergraph representation for multivariate time series without relying on prior knowledge of the data. This is achieved by applying community detection to the time series and transforming the resulting communities, obtained through an attention mechanism, into a hypergraph using a clique-based technique. Hypergraph representations are derived from different time series datasets, and the resulting hypergraphs are then used by a Dynamic Hypergraph Attention Convolution Network (DHACN) for multivariate time series predictions. This research advances the field of hypergraph representation by introducing a novel approach that is better suited to uncover high-order relationships without prior knowledge.

Marco Gregnanin, Johannes De Smedt, Giorgio Gnecco et al.

Generating synthetic data for financial time series poses challenges, especially considering their non-stationary nature. Traditional statistical time series models normally assume weak stationarity. However, this assumption can constrain their effectiveness. Deep learning models, particularly Generative Adversarial Networks (GANs), have exhibited considerable potential in emulating complex probability distributions. GANs employ a generator-discriminator framework, where the generator creates data samples, while the discriminator distinguishes real from generated data. In this research, we introduce the Sig-Graph GAN model, which integrates the time-series signature, offering a structured summary of its temporal evolution; the Long Short-Term Memory network, capturing its inherent autoregressive structure; and Graph Neural Networks (GNNs), leveraging geometric patterns within the time-series data. To employ GNNs optimally, we use the visibility graph algorithm to derive a graph-based representation of the underlying time series. Numerical evaluations demonstrate that the Sig-Graph GAN model outperforms baseline methods in replicating the distribution of logarithmic returns across different stock exchanges. The integration of the graph structure with the autoregressive component effectively captures both geometric and temporal patterns embedded in time-series data. This research advances the field of GAN models for time series by introducing a model capable of leveraging both autoregressive properties and geometric structures for synthetic data generation.

Aurélie Leribaux, Rafael Oyamada, Johannes De Smedt et al.

Understanding how actor behavior influences process outcomes is a critical aspect of process mining. Traditional approaches often use aggregate and static process data, overlooking the temporal and causal dynamics that arise from individual actor behavior. This limits the ability to accurately capture the complexity of real-world processes, where individual actor behavior and interactions between actors significantly shape performance. In this work, we address this gap by integrating actor behavior analysis with Granger causality to identify correlating links in time series data. We apply this approach to realworld event logs, constructing time series for actor interactions, i.e. continuation, interruption, and handovers, and process outcomes. Using Group Lasso for lag selection, we identify a small but consistently influential set of lags that capture the majority of causal influence, revealing that actor behavior has direct and measurable impacts on process performance, particularly throughput time. These findings demonstrate the potential of actor-centric, time series-based methods for uncovering the temporal dependencies that drive process outcomes, offering a more nuanced understanding of how individual behaviors impact overall process efficiency.

Jakob De Moor, Hans Weytjens, Johannes De Smedt et al.

Prescriptive Process Monitoring (PresPM) is an emerging area within Process Mining, focused on optimizing processes through real-time interventions for effective decision-making. PresPM holds significant promise for organizations seeking enhanced operational performance. However, the current literature faces two key limitations: a lack of extensive comparisons between techniques and insufficient evaluation approaches. To address these gaps, we introduce SimBank: a simulator designed for accurate benchmarking of PresPM methods. Modeled after a bank's loan application process, SimBank enables extensive comparisons of both online and offline PresPM methods. It incorporates a variety of intervention optimization problems with differing levels of complexity and supports experiments on key causal machine learning challenges, such as assessing a method's robustness to confounding in data. SimBank additionally offers a comprehensive evaluation capability: for each test case, it can generate the true outcome under each intervention action, which is not possible using recorded datasets. The simulator incorporates parallel activities and loops, drawing from common logs to generate cases that closely resemble real-life process instances. Our proof of concept demonstrates SimBank's benchmarking capabilities through experiments with various PresPM methods across different interventions, highlighting its value as a publicly available simulator for advancing research and practice in PresPM.

Aurelie Leribaux, Rafael Oyamada, Johannes De Smedt et al.

Predictive Process Monitoring (PPM) is a key task in Process Mining that aims to predict future behavior, outcomes, or performance indicators. Accurate prediction of the latter is critical for proactive decision-making. Given that processes are often resource-driven, understanding and incorporating actor behavior in forecasting is crucial. Although existing research has incorporated aspects of actor behavior, its role as a time-varying signal in PPM remains limited. This study investigates whether incorporating actor behavior information, modeled as time series, can improve the predictive performance of throughput time (TT) forecasting models. Using real-life event logs, we construct multivariate time series that include TT alongside actor-centric features, i.e., actor involvement, the frequency of continuation, interruption, and handover behaviors, and the duration of these behaviors. We train and compare several models to study the benefits of adding actor behavior. The results show that actor-enriched models consistently outperform baseline models, which only include TT features, in terms of RMSE, MAE, and R2. These findings demonstrate that modeling actor behavior over time and incorporating this information into forecasting models enhances performance indicator predictions.

Rafael Seidi Oyamada, Jari Peeperkorn, Jochen De Weerdt et al.

In recent years, Large Language Models (LLMs) have emerged as a prominent area of interest across various research domains, including Process Mining (PM). Current applications in PM have predominantly centered on prompt engineering strategies or the transformation of event logs into narrative-style datasets, thereby exploiting the semantic capabilities of LLMs to address diverse tasks. In contrast, this study investigates the direct adaptation of pretrained LLMs to process data without natural language reformulation, motivated by the fact that these models excel in generating sequences of tokens, similar to the objective in PM. More specifically, we focus on parameter-efficient fine-tuning techniques to mitigate the computational overhead typically associated with such models. Our experimental setup focuses on Predictive Process Monitoring (PPM), and considers both single- and multi-task predictions. The results demonstrate a potential improvement in predictive performance over state-of-the-art recurrent neural network (RNN) approaches and recent narrative-style-based solutions, particularly in the multi-task setting. Additionally, our fine-tuned models exhibit faster convergence and require significantly less hyperparameter optimization.

Jakob De Moor, Hans Weytjens, Johannes De Smedt

Prescriptive Process Monitoring (PresPM) is the subfield of Process Mining that focuses on optimizing processes through real-time interventions based on event log data. Evaluating PresPM methods is challenging due to the lack of ground-truth outcomes for all intervention actions in datasets. A generative deep learning approach from the field of Causal Inference (CI), RealCause, has been commonly used to estimate the outcomes for proposed intervention actions to evaluate a new policy. However, RealCause overlooks the temporal dependencies in process data, and relies on a single CI model architecture, TARNet, limiting its effectiveness. To address both shortcomings, we introduce ProCause, a generative approach that supports both sequential (e.g., LSTMs) and non-sequential models while integrating multiple CI architectures (S-Learner, T-Learner, TARNet, and an ensemble). Our research using a simulator with known ground truths reveals that TARNet is not always the best choice; instead, an ensemble of models offers more consistent reliability, and leveraging LSTMs shows potential for improved evaluations when temporal dependencies are present. We further validate ProCause's practical effectiveness through a real-world data analysis, ensuring a more reliable evaluation of PresPM methods.

Zhipeng He, Alexander Stevens, Chun Ouyang et al.

Adversarial attacks on tabular data present unique challenges due to the heterogeneous nature of mixed categorical and numerical features. Unlike images where pixel perturbations maintain visual similarity, tabular data lacks intuitive similarity metrics, making it difficult to define imperceptible modifications. Additionally, traditional gradient-based methods prioritise $\ell_p$-norm constraints, often producing adversarial examples that deviate from the original data distributions. To address this, we propose a latent-space perturbation framework using a mixed-input Variational Autoencoder (VAE) to generate statistically consistent adversarial examples. The proposed VAE integrates categorical embeddings and numerical features into a unified latent manifold, enabling perturbations that preserve statistical consistency. We introduce In-Distribution Success Rate (IDSR) to jointly evaluate attack effectiveness and distributional alignment. Evaluation across six publicly available datasets and three model architectures demonstrates that our method achieves substantially lower outlier rates and more consistent performance compared to traditional input-space attacks and other VAE-based methods adapted from image domain approaches, achieving substantially lower outlier rates and higher IDSR across six datasets and three model architectures. Our comprehensive analyses of hyperparameter sensitivity, sparsity control, and generative architecture demonstrate that the effectiveness of VAE-based attacks depends strongly on reconstruction quality and the availability of sufficient training data. When these conditions are met, the proposed framework achieves superior practical utility and stability compared with input-space methods. This work underscores the importance of maintaining on-manifold perturbations for generating realistic and robust adversarial examples in tabular domains.

Phuong Nam Lê, Charlotte Schneider-Depré, Alexandre Goossens et al.

Efficient planning, resource management, and consistent operations often rely on converting textual process documents into formal Business Process Model and Notation (BPMN) models. However, this conversion process remains time-intensive and costly. Existing approaches, whether rule-based or machine-learning-based, still struggle with writing styles and often fail to identify parallel structures in process descriptions. This paper introduces an automated pipeline for extracting BPMN models from text, leveraging the use of machine learning and large language models. A key contribution of this work is the introduction of a newly annotated dataset, which significantly enhances the training process. Specifically, we augment the PET dataset with 15 newly annotated documents containing 32 parallel gateways for model training, a critical feature often overlooked in existing datasets. This addition enables models to better capture parallel structures, a common but complex aspect of process descriptions. The proposed approach demonstrates adequate performance in terms of reconstruction accuracy, offering a promising foundation for organizations to accelerate BPMN model creation.

Jari Peeperkorn, Johannes De Smedt, Jochen De Weerdt

Process discovery algorithms automatically extract process models from event logs, but high variability often results in complex and hard-to-understand models. To mitigate this issue, trace clustering techniques group process executions into clusters, each represented by a simpler and more understandable process model. Model-driven trace clustering improves on this by assigning traces to clusters based on their conformity to cluster-specific process models. However, most existing clustering techniques rely on either no process model discovery, or non-stochastic models, neglecting the frequency or probability of activities and transitions, thereby limiting their capability to capture real-world execution dynamics. We propose a novel model-driven trace clustering method that optimizes stochastic process models within each cluster. Our approach uses entropic relevance, a stochastic conformance metric based on directly-follows probabilities, to guide trace assignment. This allows clustering decisions to consider both structural alignment with a cluster's process model and the likelihood that a trace originates from a given stochastic process model. The method is computationally efficient, scales linearly with input size, and improves model interpretability by producing clusters with clearer control-flow patterns. Extensive experiments on public real-life datasets show that our method outperforms existing alternatives in representing process behavior and reveals how clustering performance rankings can shift when stochasticity is considered.

Alexander Stevens, Jari Peeperkorn, Johannes De Smedt et al.

In predictive process monitoring, predictive models are vulnerable to adversarial attacks, where input perturbations can lead to incorrect predictions. Unlike in computer vision, where these perturbations are designed to be imperceptible to the human eye, the generation of adversarial examples in predictive process monitoring poses unique challenges. Minor changes to the activity sequences can create improbable or even impossible scenarios to occur due to underlying constraints such as regulatory rules or process constraints. To address this, we focus on generating realistic adversarial examples tailored to the business process context, in contrast to the imperceptible, pixel-level changes commonly seen in computer vision adversarial attacks. This paper introduces two novel latent space attacks, which generate adversaries by adding noise to the latent space representation of the input data, rather than directly modifying the input attributes. These latent space methods are domain-agnostic and do not rely on process-specific knowledge, as we restrict the generation of adversarial examples to the learned class-specific data distributions by directly perturbing the latent space representation of the business process executions. We evaluate these two latent space methods with six other adversarial attacking methods on eleven real-life event logs and four predictive models. The first three attacking methods directly permute the activities of the historically observed business process executions. The fourth method constrains the adversarial examples to lie within the same data distribution as the original instances, by projecting the adversarial examples to the original data distribution.

Alexander Stevens, Chun Ouyang, Johannes De Smedt et al.

In recent years, various machine and deep learning architectures have been successfully introduced to the field of predictive process analytics. Nevertheless, the inherent opacity of these algorithms poses a significant challenge for human decision-makers, hindering their ability to understand the reasoning behind the predictions. This growing concern has sparked the introduction of counterfactual explanations, designed as human-understandable what if scenarios, to provide clearer insights into the decision-making process behind undesirable predictions. The generation of counterfactual explanations, however, encounters specific challenges when dealing with the sequential nature of the (business) process cases typically used in predictive process analytics. Our paper tackles this challenge by introducing a data-driven approach, REVISEDplus, to generate more feasible and plausible counterfactual explanations. First, we restrict the counterfactual algorithm to generate counterfactuals that lie within a high-density region of the process data, ensuring that the proposed counterfactuals are realistic and feasible within the observed process data distribution. Additionally, we ensure plausibility by learning sequential patterns between the activities in the process cases, utilising Declare language templates. Finally, we evaluate the properties that define the validity of counterfactuals.

Alexandre Goossens, Johannes De Smedt, Jan Vanthienen

Organizations execute decisions within business processes on a daily basis whilst having to take into account multiple stakeholders who might require multiple point of views of the same process. Moreover, the complexity of the information systems running these business processes is generally high as they are linked to databases storing all the relevant data and aspects of the processes. Given the presence of multiple objects within an information system which support the processes in their enactment, decisions are naturally influenced by both these perspectives, logged in object-centric process logs. However, the discovery of such decisions from object-centric process logs is not straightforward as it requires to correctly link the involved objects whilst considering the sequential constraints that business processes impose as well as correctly discovering what a decision actually does. This paper proposes the first object-centric decision-mining algorithm called Integrated Object-centric Decision Discovery Algorithm (IODDA). IODDA is able to discover how a decision is structured as well as how a decision is made. Moreover, IODDA is able to discover which activities and object types are involved in the decision-making process. Next, IODDA is demonstrated with the first artificial knowledge-intensive process logs whose log generators are provided to the research community.

Alexander Stevens, Johannes De Smedt

Although a recent shift has been made in the field of predictive process monitoring to use models from the explainable artificial intelligence field, the evaluation still occurs mainly through performance-based metrics, thus not accounting for the actionability and implications of the explanations. In this paper, we define explainability through the interpretability of the explanations and the faithfulness of the explainability model in the field of process outcome prediction. The introduced properties are analysed along the event, case, and control flow perspective which are typical for a process-based analysis. This allows comparing inherently created explanations with post-hoc explanations. We benchmark seven classifiers on thirteen real-life events logs, and these cover a range of transparent and non-transparent machine learning and deep learning models, further complemented with explainability techniques. Next, this paper contributes a set of guidelines named X-MOP which allows selecting the appropriate model based on the event log specifications, by providing insight into how the varying preprocessing, model complexity and explainability techniques typical in process outcome prediction influence the explainability of the model.

Johannes De Smedt, Anton Yeshchenko, Artem Polyvyanyy et al.

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

Boudewijn van Dongen, Johannes De Smedt, Claudio Di Ciccio et al.

Mixed-paradigm process models integrate strengths of procedural and declarative representations like Petri nets and Declare. They are specifically interesting for process mining because they allow capturing complex behaviour in a compact way. A key research challenge for the proliferation of mixed-paradigm models for process mining is the lack of corresponding conformance checking techniques. In this paper, we address this problem by devising the first approach that works with intertwined state spaces of mixed-paradigm models. More specifically, our approach uses an alignment-based replay to explore the state space and compute trace fitness in a procedural way. In every state, the declarative constraints are separately updated, such that violations disable the corresponding activities. Our technique provides for an efficient replay towards an optimal alignment by respecting all orthogonal Declare constraints. We have implemented our technique in ProM and demonstrate its performance in an evaluation with real-world event logs.

Johannes De Smedt, Jochen De Weerdt

The field of predictive process monitoring focuses on case-level models to predict a single specific outcome such as a particular objective, (remaining) time, or next activity/remaining sequence. Recently, a longer-horizon, model-wide approach has been proposed in the form of process model forecasting, which predicts the future state of a whole process model through the forecasting of all activity-to-activity relations at once using time series forecasting. This paper introduces the concept of \emph{predictive process model monitoring} which sits in the middle of both predictive process monitoring and process model forecasting. Concretely, by modelling a process model as a set of constraints being present between activities over time, we can capture more detailed information between activities compared to process model forecasting, while being compatible with typical predictive process monitoring objectives which are often expressed in the same language as these constraints. To achieve this, Processes-As-Movies (PAM) is introduced, i.e., a novel technique capable of jointly mining and predicting declarative process constraints between activities in various windows of a process' execution. PAM predicts what declarative rules hold for a trace (objective-based), which also supports the prediction of all constraints together as a process model (model-based). Various recurrent neural network topologies inspired by video analysis tailored to temporal high-dimensional input are used to model the process model evolution with windows as time steps, including encoder-decoder long short-term memory networks, and convolutional long short-term memory networks. Results obtained over real-life event logs show that these topologies are effective in terms of predictive accuracy and precision.