Benoît Depaire

Jan Mendling, Benoît Depaire, Henrik Leopold

There is an ongoing debate in computer science how algorithms should best be studied. Some scholars have argued that experimental evaluations should be conducted, others emphasize the benefits of formal analysis. We believe that this debate less of a question of either-or, because both views can be integrated into an overarching framework. It is the ambition of this paper to develop such a framework of algorithm engineering with a theoretical foundation in the philosophy of science. We take the empirical nature of algorithm engineering as a starting point. Our theoretical framework builds on three areas discussed in the philosophy of science: ontology, epistemology and methodology. In essence, ontology describes algorithm engineering as being concerned with algorithmic problems, algorithmic tasks, algorithm designs and algorithm implementations. Epistemology describes the body of knowledge of algorithm engineering as a collection of prescriptive and descriptive knowledge, residing in World 3 of Popper's Three Worlds model. Methodology refers to the steps how we can systematically enhance our knowledge of specific algorithms. In this context, we identified seven validity concerns and discuss how researchers can respond to falsification. Our framework has important implications for researching algorithms in various areas of computer science.

Toon Jouck, Alfredo Bolt, Benoît Depaire et al.

Process mining offers techniques to exploit event data by providing insights and recommendations to improve business processes. The growing amount of algorithms for process discovery has raised the question of which algorithms perform best on a given event log. Current evaluation frameworks for empirically evaluating discovery techniques depend on the notation used (behavioral identical models may give different results) and cannot provide more general statements about populations of models. Therefore, this paper proposes a new integrated evaluation framework that uses a classification approach to make it modeling notation independent. Furthermore, it is founded on experimental design to ensure the generalization of results. It supports two main evaluation objectives: benchmarking process discovery algorithms and sensitivity analysis, i.e. studying the effect of model and log characteristics on a discovery algorithm's accuracy. The framework is designed as a scientific workflow which enables automated, extendable and shareable evaluation experiments. An extensive experiment including four discovery algorithms and six control-flow characteristics validates the relevance and flexibility of the framework. Ultimately, the paper aims to advance the state-of-the-art for evaluating process discovery techniques.