| |
|
Detailed schedule
Click on a link for more details
Show all the abstracts
Thursday 30 January:
Thursday 11:15-12:30 TA-1: COMEX - Optimization 1
Room Vesale 023 - Chair: M. Schyns
Thursday 11:15-12:30 TA-2: Software and Implementation
Room Vesale 020 - Chair: M. Mezmaz
Thursday 11:15-12:30 TA-3: COMEX - Smart mobility
Room Vesale 025 - Chair: A. Caris
Thursday 11:15-12:30 TA-4: Systems
Room Pentagone 0A11 - Chair: P. Kunsch
Thursday 14:00-15:40 TB-1: Data Analysis 1
Room Vesale 023 - Chair: X.Siebert
- Early detection of university students in potential difficulty
Anne-sophie Hoffait (HEC - University of Liege)
Co-authors: M;Schyns
Abstract:
Access to the Belgian higher education system is easier and cheaper than in most foreign countries. Moreover, the quality of our Universities is acknowledged and the degrees they deliver could be considered as a must.
As a consequence, lots of candidates apply.
However, while access is relatively open, it is not a free lunch and a large proportion of candidates do not satisfy the requirements at the end of the first year. This has a cost for the students (fees, one year lost, frustration...) but also for the collectivity (the Universities are funded by the Government) and for the Universities (lots of ressources are needed).
It is therefore important to try to identify as early as possible the students that could potentially be in difficulty during the first year. The Universities might then take appropriate measures to alleviate the problem.
There are indeed various reasons that could explain a failure and some that could be dealt with: a wrong orientation (e.g. due to a lack of correct information), a misinterpretation of the requirements and expectations of a university degree, a huge difficulty in making the transition from the high education system to the higher education system, an insufficient mastery of some prerequisite concepts... The University of Li\`ege, as other Universities, has already taken different initiatives. But, if we were able to early identify with a high probability those students, the Universities might develop adapted methods to attack the problem with more emphasis where it is more needed and when it is still possible.
Our contribution is multiple. First, the aim is to develop a decision tool able to identify the students who have a high probability to face difficulties if nothing is done to help them. For that, we consider three standard datamining methods: logistic regression, artificial neural networks and decision trees and focus on early detection, i.e. before starting at the University.
Secondly, we suggest to adapt these three methods as well as the classification framework in order to increase the probability of correct identification of the students. In our approach,we do not restrict the classification to two extreme classes, e.g. failure or succes, but we create subcategories for different levels of confidence: high risk of failure, risk of failure, expected success or high probability of success. The algorithms are modified accordingly and to give more weight to the class that really matters.
Note that this approach remains valid for any other classification problems for which the focus is on some extreme classes; e.g. fraud detection, credit default...
Finally, simulations are conducted to measure the performances of the three methods, with and without the suggested adaptation. We check if the factors of success/failure we can identify are similar to those reported in the literature.
We also make a ``what-if sensitivity analysis''. The goal is to measure in more depth the impact of some factors and the impact of some solutions, e.g., a complementary training or a reorientation.
- MediaCycle : A tool for interactive browsing of multimedia libraries.
Xavier Siebert (Faculté Polytechnique de Mons)
Co-authors: Thierry Ravet, Christian Frisson, Stéphane Dupont
- First species counterpoint music generation with VNS and vertical viewpoints
Dorien Herremans (Universiteit Antwerpen)
Co-authors: Kenneth Sörensen, Darrell Conklin
- A Choquet integral for the comparison of decisional maps
Valerie Brison (UMONS)
Co-authors: Marc Pirlot
Thursday 14:00-15:40 TB-2: Multiple Objectives
Room Vesale 020 - Chair: Y. de Smet
Thursday 14:00-15:40 TB-3: Logistics
Room Vesale 025 - Chair: D. De Wolf
Thursday 14:00-15:40 TB-4: COMEX - Applications to Economy
Room Pentagone 0A11 - Chair: W. Brauers
Thursday 14:00-15:40 TB-5: Networks
Room Pentagone 0A07 - Chair: B. Fortz
Thursday 16:10-17:25 TC-1: Mixed-integer nonlinear programming
Room Vesale 023 - Chair: Y. Crama
Thursday 16:10-17:25 TC-2: Decision Analysis 1
Room Vesale 020 - Chair: S. Eppe
Thursday 16:10-17:25 TC-3: Routing
Room Vesale 025 - Chair: K. Sörensen
Thursday 16:10-17:25 TC-4: Graphs
Room Pentagone 0A11 - Chair: H. Mélot
Thursday 16:10-17:25 TC-5: Scheduling
Room Pentagone 0A07 - Chair: S. Hanafi
Friday 9:00-10:15 FA-1: Queuing
Room Vesale 023 - Chair: S. Wittevrongel
Friday 9:00-10:15 FA-2: Decision Analysis 2
Room Vesale 020 - Chair: R. Bisdorff
Friday 9:00-10:15 FA-3: COMEX - Optimization 2
Room Vesale 025 - Chair: M. Labbé
Friday 9:00-10:15 FA-4: Production
Room Pentagone 0A11 - Chair: D. Tuyttens
Friday 14:00-15:40 FB-1: Data Analysis 2
Room Vesale 023 - Chair: P. Fortemps
Friday 14:00-15:40 FB-2: Heuristics
Room Vesale 020 - Chair: T. Stützle
Friday 14:00-15:40 FB-3: COMEX - Transportation
Room Vesale 025 - Chair: F. Spieksma
Friday 14:00-15:40 FB-4: Health
Room Pentagone 0A11 - Chair: G. Vanden Berghe
|
|
