First, we introduce SOPA (Sustainability-Oriented Process Analysis and Re-design), a framework that integrates Life Cycle Assessment (LCA) with Activity-Based Costing (ABC) to assess the environmental impact of business processes. SOPA enables sustainability analysis using either process execution data or simulation-based data, providing a structured approach for organizations to evaluate and mitigate their environmental footprint. I will present the conceptual foundation of SOPA and its practical implementation.

Second, we address the visualization gap in process analysis on the example of conformance checking, a core process mining operation used to assess whether observed process executions align with predefined models. It can be for example used to assess whether business processes comply with regulatory regarding reducing the environmental impact (e.g., EU taxonomy). Despite its significance, conformance checking remains underutilized in existing process mining tools due to the lack of intuitive and effective visualization techniques. To tackle this, we propose a task taxonomy for conformance checking visualization, offering a structured framework to guide the design of visualization tools that enhance the interpretability of compliance results for diverse stakeholders.

By integrating sustainability-driven process analysis, regulatory conformance checking, and advanced visual analytics, this talk aims to expand the capabilities of Business Process Analysis.

Performance improvements in machine learning techniques do not usually come for free. Notions of complexity and opaqueness are common labels of machine learning-based models. Having the business process stakeholders at the center of focus in PPM necessitates mitigating the consequences of the opaqueness associated with complex predictive models. Explainability tends to increase trust in the generated predictions and boost human interaction with predictive models as a result of increased understanding and transparency.
Furthermore, explanations may be utilized to uncover potential problems resulting from the
training of a predictive model on biased data and improve the performance of the predictive
model. Several eXplainable Artificial Intelligence (XAI) methods have been proposed, but
the right mechanisms to evaluate their application should be in place in order to apply them.
However, evaluating XAI in the context of PPM is a difficult task, due to the lack of a shared
and accepted definition of explainability and its associated characteristics and evaluation
criteria.

The contributions of this thesis include an analysis framework designed to systematically investigate the implications of applying different PPM techniques on explainability from different perspectives. As a second contribution, an approach to evaluate global explainability methods is proposed. This approach analyzes the consistency of explanations when compared with data-related facts extracted from business process data. As a final contribution, the thesis introduces an approach to assess the interpretability of explanations produced for specific predictions. In particular, the proposed approach considers rule-based explanations according to different interpretability-related criteria. The thesis further discusses the results and lessons learned using a number of experiments that follow different settings. As a merit of this research, all contributions were validated from a PPM perspective based on real-life process-related data.

The rising prevalence of mental and behavioral disorders in recent years has significantly strained existing healthcare resources. This strain has manifested in extended waiting periods, resulting in a notable treatment gap where individuals often fail to receive timely and adequate support. The global disparity in resource allocation exacerbates these challenges, with more severe consequences observed in underserved regions. In response, recent innovations in digital technology have prompted researchers to explore new methods to bridge this treatment gap. Notably, the introduction of internet- and mobile-based interventions (IMIs) delivered through eHealth platforms has marked a significant development. These interventions are being proven effective in managing various mental and behavioral disorders, and they are cost-efficient. However, the expansion of IMIs encounters significant hurdles, primarily due to issues of low user adherence and engagement, which diminish their overall effectiveness.

This work presents persuasive design strategies for optimizing eHealth platforms to improve user adherence and engagement. Utilizing a comprehensive methodological framework, the research begins with a requirement analysis and a scoping review to identify essential features, user needs, and existing development methodologies. Based on these insights, randomized controlled trials (RCTs) were implemented to assess changes in user adherence and engagement. Advanced usability analyses were then performed using measurement technologies such as eye tracking to deeply investigate usability issues. The resulting data were further analyzed and interpreted through the application of machine learning techniques, providing a robust approach to enhancing eHealth platform design and functionality.

Overall, the developed optimization strategies aim to improve user adherence and engagement in eHealth platforms, thereby enhancing their overall effectiveness.