Logo UHasselt

menu

Business Informatics (BINF)


News

News

Logo UHasselt Universiteit Hasselt - Knowledge in action

PAST EVENTS

BI-day 2020: a productive day with AE

19/02/2020

The case of the annual BI-day with our Business Informatics students, provided by AE - architects for business & ICT, centred around innovative and creative thinking in a healthcare context. Students came up with very useful ideas such as an app for blood donations and keeping track of your vaccinations.

 

Round table about event analytics

08&22/11/2019

As further research in transforming event data into business value is required, use cases in cooperation with business were identified. Knowing what business needs and wants w.r.t. exploiting the potential of event data is an excellent starting point in defining research goals for our behavioural analytics area in the research group. This was done in the format of a round table talk with 9 Flemish companies, engaging in open talks on their business needs and technical challenges. One discovered use case is, among others, tracking sensor data of IT hardware in order to predict server downtimes and reduce the duration of this downtime to a minimum. Our partners reached a general consensus on the desire to perform a more data-driven operational excellence and to understand their customers’ behaviour in order to improve products and services.

As creating business value with IT is one of our research group’s main goals, a continuing close cooperation with industry is of the utmost importance. We shall certainly reach out again for valuable input when it is required.

 

Business Informatics trip 2019: VivaTech Paris

16-17/05/2019

Every year we organise an educational (and also fun) trip for our business informatics students. This year’s trip took us to Paris! We attended Viva Technology, a yearly event about everything that is technology-related. This year the event was all about positive innovation (“Tech for good”). 

 

Workshop on Fuzzy Cognitive Maps

29-30/10/2018

There is no doubt about the current role of Machine Learning in the fascinating world of Business Intelligence. Predicting whether a customer will be loyal to the company or not, understanding customers’ behaviour or anticipating market fluctuations are typical examples on which Machine Learning may be pivotal. Unfortunately, most successful Machine Learning algorithms like Random Forests, Neural Networks or Support Vector Machines do not provide any mechanism to explain how they arrived at a particular conclusion and behave like a “black box”. This means that they are neither transparent  nor interpretable. We could understand transparency as the algorithm’s ability to explain its reasoning mechanism, while interpretability refers to the algorithm’s ability to explain the semantics behind the problem domain.

In recent years, we have been investigating Fuzzy Cognitive Maps (FCMs) as a vehicle to design accurate and interpretable Machine Learning algorithms. During the workshop on Fuzzy Cognitive Maps (FCMs), researchers from all over the world discussed and analysed potential shortcomings of FCMs to stimulate research even more.

 

The future of conformance checking: identifying challenges and opportunities

8-9/02/2018

On the 8th and 9th of February 2018, we gathered with an international group of process mining researchers to discuss the many challenges in the field of conformance checking. The event was organized by the Flemish Scientific Research Community on Process Mining (https://www.srcprocessmining.org), a community that is led by our research group, together with KULeuven and UGent. The brainstorm session was attended by researchers from the Polytechnic University of Catalonia, the Pontifical Catholic University of Chile,  RWTH Aachen University, the Technical University of Eindhoven and the Wirtschaftsuniversität Wien.

In an aptly historical setting, on the former grounds of the mining site of Eisden, far away from the familiar course of academic life, attendants were challenged to take part in several discussions on the future of conformance checking, articulating shortcomings of current techniques as well as opportunities and challenges for the field.

On the agenda were several topics: the need for clear use cases, trade-offs and hierarchies between quality dimensions, the role of generalization, desirable properties for quality metrics, etc. Which are the kind of conformance checking tools that practitioners expect, and how is the research field able to currently provide these? What can we learn from other fields, such as data science and statistics? And for which problems do we fail to propose appropriate solutions? Plenty of topics for future research, no doubt about that.

As outcome of the two-day brainstorm, the participants committed to publishing a Conformance Checking Manifesto, which will create a shared foundation of terminology, key concepts and use cases, as well as indicate the many challenges ahead. As a result, it will serve as a guide for current and prospective researchers in the conformance checking area.

In between the discussions there were several refreshing break-out moments, including ascents of the historical mine shaft as well as the mine spoil bank, and a guided tour of the UHasselt Ecotron, a field research facility with climate-controlled units for the measurements of complex ecological processes. I think we can look back at a very fruitful and pleasant brainstorm session and look forward to follow-up actions.