Marwan Hassani

Predictive Process Monitoring (PPM) forecasts future events of ongoing business processes based on event logs. However, deep learning approaches to PPM are often limited by labeled data scarcity and the low variability of real-world logs. To address this, we introduce SiamSA-PPM, a self-supervised framework combining Siamese learning with statistically grounded data augmentation. It employs novel transformation methods that leverage control-flow semantics and frequent behavioral patterns to generate realistic, semantically valid trace variants, learning generalizable prefix representations without labeled supervision. Extensive experiments on real-world event logs with a wide range of variability, incorporating exhaustive hyperparameter tuning, demonstrate the value of this process-aware augmentation. Compared to state-of-the-art baselines, SiamSA-PPM achieves competitive or superior predictive performance in both next activity and final outcome prediction tasks. An open-source implementation of our method is publicly available at https://github.com/SvStraten/SiamSA-PPM-IJCIS .

Predictive process monitoring (PPM) focuses on predicting future process trajectories, including next activity predictions. This is crucial in dynamic environments where processes change or face uncertainty. However, current frameworks often assume a static environment, overlooking dynamic characteristics and concept drifts. This results in catastrophic forgetting, where training while focusing merely on new data distribution negatively impacts the performance on previously learned data distributions. Continual learning addresses, among others, the challenges related to mitigating catastrophic forgetting. This paper proposes a novel approach called Continual Next Activity Prediction with Prompts (CNAPwP), which adapts the DualPrompt algorithm for next activity prediction to improve accuracy and adaptability while mitigating catastrophic forgetting. We introduce new datasets with recurring concept drifts, alongside a task-specific forgetting metric that measures the prediction accuracy gap between initial occurrence and subsequent task occurrences. Extensive testing on three synthetic and two real-world datasets representing several setups of recurrent drifts shows that CNAPwP achieves SOTA or competitive results compared to five baselines, demonstrating its potential applicability in real-world scenarios. An open-source implementation of our method, together with the datasets and results, is available at: https://github.com/SvStraten/CNAPwP .

Detecting anomalies in business processes is essential for maintaining operational efficiency and preventing fraud or misuse. Although process mining enables automated anomaly detection (AD), most methods provide only binary outputs and struggle to distinguish between different anomaly perspectives, handle variable-length event sequences, or detect numerical anomalies—especially in online settings where early detection is critical. This work presents MP-Former, a Transformer-based AD model designed for online, multi-perspective anomaly detection. Using a multi-task learning architecture, MP-Former simultaneously predicts multiple anomaly perspectives with high detail and computational efficiency. We further introduce two novel perspectives—arrival, time and workload, capturing the temporal and inter-case dependencies, which are often overlooked in prior research. Experimental evaluation shows that MP-Former achieves superior F1-scores across all perspectives while maintaining real-time performance, demonstrating the value of specialized multi-perspective approaches for accurate and efficient process anomaly detection.

Continual learning, known also as lifelong learning, aims at designing learning models that can continuously and autonomously adapt to varying data concepts without forgetting previously collected knowledge. Such concepts are referred to as tasks. Predictive business process monitoring, which predicts future process steps, is crucial in dynamic environments where tasks are not previously specified and processes frequently change or face unpredictability. However, many existing frameworks assume a static setting, ignoring dynamic nature and concept drifts in processes, leading to catastrophic forgetting—where training over new data adversely affects the performance on previously learned tasks. This paper presents TFCLPM, a framework for online next activity prediction that operates without relying on predefined tasks and employs continual learning techniques to reduce catastrophic forgetting. The methodology combines a Single Dense Layer neural network with a continual learning algorithm designed to retain challenging historical samples and include a regularizer to stabilize model parameters. Additionally, our approach introduces a diversity-aware memory updating strategy, ensuring that retained samples remain representative of the overall data distribution, leading to more stable adaptation and improved long-term retention. Extensive experimental evaluations with synthetic and real-world event logs highlight our optimal configurations. The proposed framework's performance is compared against three existing online next activity prediction methodologies. Results show significant improvements in prediction accuracy, especially in scenarios with gradual or recurrent drifts, highlighting the framework’s robustness and efficiency, even with larger datasets with multiple classes.

Continual learning, known also as lifelong learning, aims at designing learning models that can continuously and autonomously adapt to varying data concepts without forgetting previously collected knowledge. Such concepts are referred to as tasks. Predictive business process monitoring, which predicts future process steps, is crucial in dynamic environments where tasks are not previously specified and processes frequently change or face unpredictability. However, many existing frameworks assume a static setting, ignoring dynamic nature and concept drifts in processes, leading to catastrophic forgetting—where training over new data adversely affects the performance on previously learned tasks. This paper presents TFCLPM, a framework for online next activity prediction that operates without relying on predefined tasks and employs continual learning techniques to reduce catastrophic forgetting. The methodology combines a Single Dense Layer neural network with a continual learning algorithm designed to retain challenging historical samples and include a regularizer to stabilize model parameters. Extensive experimental evaluations with synthetic and real-world event logs highlight our optimal configurations. The proposed framework’s performance is compared against three existing online next activity prediction methodologies. Results show significant improvements in prediction accuracy, especially in scenarios with gradual or recurrent drifts, highlighting the framework’s robustness and efficiency, even with large datasets.