Bart Hamers, Ph.D.
greatest difficulty in the world is not for people to accept new ideas, but to
make them forget old ideas."
My name is Bart Hamers. I am a Professional Analyst with both strong academic and business experience. My main sphere of interests is Information Management for Predictive Analytics. I am interested how companies use their Information and Data in the most efficient and way. How should information be captured, stored, treated, used and communicated with as final goal efficient decision support.
Information Management for Predictive Analytics overlaps with different sub domains: Data Governance, Business Intelligence, Data Mining, and Statistical and Mathematical Modeling. I had the opportunity to apply these techniques in Banking, Marketing and Telco.
Recently I am interested in the data governance for quantitative business solutions in terms of both IT, mathematical and project mode. How should one structure a quantitative decision support team within an operational business environment. This involves typically 3 phases:
All of them have to align in order to have highest efficiency of your project. But also the project management of quantitative modeling projects is al challenging topic. Less is known about this topic since data mining projects typically live between IT and R&D.
Here you can find a detailed description of my CV. (English).
Since April 2010: Head of Data Governance, Risk Management Department of the Dexia s.a.
My job focus lies in in the domain of Credit and Operational Risk. My main tasks are
April 2006-April 2010: Senior Quantitative Analyst, Risk Management, Dexia s.a.
March 2005 -Januari 2006: Marketing Data Mining Consultancy in Telco, IKAN Consulting.
March 2004 - March 2005:
Marketing Data Mining Consultancy
in Telco and Banking,
(Part of the WegenerDM direct marketing
Teaching and Research Assistant at the Department of Electrical Engineering, KUL (ESAT/SCD-SISTA)
August 1999-March 2004: Teaching and Research Assistant at the Department of Electrical Engineering, KUL (ESAT/SCD-SISTA)
June 2004: PhD in Applied Sciences, KUL (ESAT/SCD- SISTA)
June 1999: Master of Science in Artificial Intelligence at the KUL
Master thesis: ‘A neural network model of grouping by proximity in dot lattices’
June 1997: Master of Science in Physics, Katholieke Universiteit Leuven (KUL), Leuven, Belgium
Graduated cum laude Option: Nuclear Physics
Senior thesis: ‘Study of tensor activity in nuclear ß-decay by means of nuclear orientation methods’; Supervisors: prof. dr. Nathal Severijns (IKS, KUL)
September 1995: Associate degree in Physics, Limburgs Universitair Centrum , Diepenbeek, Belgium
Kernel Models for Large Scale Applications
As a result of the ever-growing influence of IT in research and companies terabytes of data are handled and stored daily. Therefore the interest in using this source of information is increasing steadily. It is there that data mining and machine learning gives us a hand. One recently developed set of tools in data mining are kernel models. These models excel in a variety of problem situations like classification, regression, time-series prediction problems with respect to the generalization performance tested on unseen data. The disadvantage of these models is that the computational demands for training them scale quadratically with the size of the training set. In this work we will show how this scalability problem for kernel models can be overcome by making use of a combination of methods from numerical and learning theory origin.
The proposed solutions, which have to be taken into account when one wants to use kernel models on large scale applications, will be presented on the basis of five pillars. These five pillars are: the model choice, the numerical procedures, the choice of the kernel, low rank approximations and the use of ensemble models. First we will show how models using a quadratic loss function will have a training procedure that consists of a linear system. We will show how iterative methods and low rank approximations can reduce the computational and memory complexity for solving this linear system. Also we will show that the kernel itself plays an important role in both the learning performance and the computational and memory complexity of the algorithms.
As a last solution we will propose the use of ensemble models for training kernel models on large data sets. Instead of training one model on a training set, a whole set of models is trained on subsets of the original training set. In this way the scalability problem can be avoided. In addition we will introduce a new method of coupled learning. In this methodology the members of the ensemble will share the knowledge during training. This leads to a new way of transductive learning.
The results of this research have contributed in the development of the Matlab LS_SVMlab package. To download this free software package visit the webpage.
|Publications & Reports|
K. Dejaeger, B. Hamers, J.Poelmans, B.Baesens, A novel approach to the evaluation and improvement of data quality in the financial sector. Proceedings of 15th International Conference on Information Quality (ICIQ 2010), International Conference on Information Quality (ICIQ 2010)
Karel Dejaeger, Jessica Ruelens, Tony Van Gestel, Joachim Jacobs, Bart Baessens, Jonas Poelmans, Bart Hamers, Evaluatie en verbetering van Datakwaliteit, Informatie, November 2009.
Gerd Castermans, David Martens, Tony Van Gestel, Bart Hamers, Bart Baesens, An Overview and Framework for PD Backtesting and Benchmarking, Journal of the Operational Research Society, 2007
Pelckmans K., Suykens J.A.K., Van Gestel T., De Brabanter J., Lukas L., Hamers B., DE Moor B., Vandewalle J., `` L S-SVMlab : a Matlab/C toolbox for Least Squares Support Vector Machines'', Internal Report 02-44, ESAT-SISTA, K.U.Leuven (Leuven, Belgium), 2002.
Hamers B., Suykens J.A.K., De Moor B., ``A comparison of iterative methods for least squares support vector machine classifiers'', Internal Report 01-110, ESAT-SISTA, K.U.Leuven (Leuven, Belgium), 2001.
Hamers B., Suykens J.A.K., De Moor B., ``Coupled Transductive Ensemble Learning of Kernel Models'', Internal Report 03-172, ESAT-SISTA, K.U.Leuven (Leuven, Belgium), 2003.
Hamers B., Suykens J.A.K., Leemans V. De Moor B., ``Ensemble Learning of Coupled Parameterized Kernel Models'',in Proceedings ICANN/ICONIP 2003, Istanbul, Turkey.
Hamers B., Suykens J.A.K., De Moor B., ``Compactly supported RBF kernels for sparsifying the Gram matrix in LS-SVM regression models'', in Proceedings ICANN 2002, Madrid, Spain, August 2002, pp 720-726.
|Professional Talks 2007-now|
Advanced Internal Rating-Based (AIRB) Credit Risk Modeling Using MATLAB,
Matlab Computational Finance Virtual Conference, 2011.
Hamers B, G. Castermans, Basel 2 AIRB Credit Risk Modeling using MATLAB, Matlab Seminars, Spring 2010.
Hamers B., Estimating Loss Given Default (LGD) and measuring recovery rates, Asia Risk Training, Hong Kong, November 2007.
|Master Thesis's under my supervision 2007-now|
Evolutions in the Backtesting Framework, VIE, 2011-now.
Alexandre Foray, Automated Data Preparation for Pillar 2 Portfolio Modeling, VIE, 2010.
Koen Robyns, Hans Dejonge, Quantitative techniques for data quality management, Master Thesis, 2009-2010
Karel Dejaeger, Jessica Ruelens, Datakwaliteit in Risk Management, Master Thesis, 2008-2009.
Afef Ben Khaled, Statistical Analysis of Operational Risk Data, VIE, 2008-2009.
Koen Berteloot, Statistical Survival Analysis applied on Default Risk, Stage, KULeuven,2007.
Koningin Astridlaan 42, 3010 Leuven, Belgium
mobile: +32 479 90 06 67
Email: follow the link
Informative Sites about AI, Neural Networks, Machine Learning and philosophy
Hobbies and Fun:
Also visit the site of my beautiful children Siebe and Cléo
I'm also a big fan of: