The Vlerick Repository is a searchable Open Access publication database, containing the complete archive of research output (articles, books, cases, doctoral dissertations,…) written by Vlerick faculty and researchers and preserved by the Vlerick Library.
Find out more about Open Access.
Call to action!
Making your past and future work Open Access in the Vlerick Repository is easy. Send the details of your research output (incl. post-print version) to firstname.lastname@example.org.
Communities in Vlerick Repository
Select a community to browse its collections.
From one-class to two-class classification by incorporating expert knowledge: Novelty detection in human behaviour (Published Online)One-class classification is the standard procedure for novelty detection. Novelty detection aims to identify observations that deviate from a determined normal behaviour. Only instances of one class are known, whereas so called novelties are unlabelled. Traditional novelty detection applies methods from the field of outlier detection. These standard one-class classification approaches have limited performance in many real business cases. The traditional techniques are mainly developed for industrial problems such as machine condition monitoring. When applying these to human behaviour, the performance drops significantly. This paper proposes a method that improves existing approaches by creating semi-synthetic novelties in order to have labelled data for the two classes. Expert knowledge is incorporated in the initial phase of this data generation process. The method was deployed on a real-life test case where the goal was to detect fraudulent subscriptions to a telecom family plan. This research demonstrates that the two-class expert model outperforms a one-class model on the semi-synthetic dataset. In a next step the model was validated on a real dataset. A fraud detection team of the company manually checked the top predicted novelties. The results show that incorporating expert knowledge to transform a one-class problem into a two-class problem is a valuable method.
Five years of the Vlerick Energy Centre. An overview of results and lessons learnedAn overview of results and lessons learned from five years of the Vlerick Energy Centre. Energy concerns all of us. Being intertwined with the debate on decarbonisation and climate change, energy is a potentially hot topic. Two extreme positions have attracted significant media coverage during the past year. At one end of the spectrum are those people who feel the transition cannot happen fast enough, engaging in climate protests inspired by Greta Thunberg. At the other end are the Gilets Jaunes, applying the brakes because they believe, on the contrary, that things are moving too fast and life has become too expensive.
Creating high-trust cultures - what can we learn from Belgium's best workplacesWhat can we learn from Belgium’s Best Workplaces™ when it comes to people practices? Organisations are reinventing themselves to keep pace with the challenges of this fluid, unpredictable world. Both local and global markets are transforming continuously, and new digital technologies and business models are causing a significant level of disruption. Enterprises are being forced to rethink their existing structures and to continuously improve themselves.