738 research outputs found
Building intelligent credit-risk evaluation systems using neural network rule extraction and decision tables
No full textTable of contentsNeo-classical reengineering: Returning to the promise of process in the post-Internet economyM. De Kegel and M. McDonaldTowards an integrative framework for software architectureR. Maes and G. DedeneComponent based development. From dinosaurs to small, adaptive, co-operating, replaceable creaturesG. Van Humbeeck, J. MerckxSeparating Business Process Aspects from Business Object behaviourM. SnoeckCOSMIC-FFP and MERODE: Applying the Next Generation Function Points to Object Oriented Enterprise ModelsG. PoelsOn the use of Jackson Structured Programming (JSP) for the structured design of XSL TransformationsG. DedeneRuling the business: about Business Rules, decision tables and Intelligent AgentsJ. VanthienenBuilding intelligent credit-risk evaluation systems using neural network rule extraction and decision tablesB. Baesens, R. Setiono, C. Mues, S. Viaene and J. VanthienenWeb service description, advertising and discovery: WSDL and beyondW. LemahieuDeveloping enterprise architecture: the case of KBC InsuranceF. Pieck, S. Viaene and G. Deden
Shared for publication.zip
No full textSupplemental information to Viaene et al. 2023:
Extrapolation of metal toxicity data for the rotifer Brachionus calyciflorus using an individual-based population model
Authors: Karel P. J. Viaene*, Karel A. C. De Schamphelaere, Patrick Van Sprang
Contains the raw data, Netlogo code and simulations and the R code to analyse the data. </p
Post-processing of association rules
No full textIn this paper, we situate and motivate the need for a post-processing phase to the association rule mining algorithm when plugged into the knowledge discovery in databases process. Major research effort has already been devoted to optimising the initially proposed mining algorithms. When it comes to effectively extrapolating the most interesting knowledge nuggets from the standard output of these algorithms, one is faced with an extreme challenge, since it is not uncommon to be confronted with a vast amount of association rules after running the algorithms. The sheer multitude of generated rules often clouds the perception of the interpreters. Rightful assessment of the usefulness of the generated output introduces the need to effectively deal with different forms of data redundancy and data being plainly uninteresting. In order to do so, we will give a tentative overview of some of the main post-processing tasks, taking into account the efforts that have already been reported in the literature.status: Publishe
The Trade and FDI Effects of EMU Enlargement
No full textThis paper considers the nature and the distribution of trade and FDI effects of a potential enlargement of the European Monetary Union (EMU) to the ten countries that obtained EU membership in 2004. One-way and two-way error component gravity models are estimated using a dataset of unbalanced panel data that combines bilateral trade flows among 29 countries and the distribution of outward FDI stocks among these countries. The results reveal a complementarity between trade and investment and a relationship between trade and exchange rate volatility that depends on the sign of bilateral trade balances. Using a simulation-based technique, we find that estimates of FDI effects of EMU range between 18.5 percent for Poland and 30 percent for Hungary.EMU, exchange rate volatility, foreign investment, trade diversion, vertical integration
Benchmarking state-of-the-art classification algorithms for credit scoring
No full textIn this paper, we study the performance of various state-of-the-art classification algorithms applied to eight real-life credit scoring data sets. Some of the data sets originate from major Benelux and UK financial institutions. Different types of classifiers are evaluated and compared. Besides the well-known classification algorithms (eg logistic regression, discriminant analysis, k-nearest neighbour, neural networks and decision trees), this study also investigates the suitability and performance of some recently proposed, advanced kernel-based classification algorithms such as support vector machines and least-squares support vector machines (LS-SVMs). The performance is assessed using the classification accuracy and the area under the receiver operating characteristic curve. Statistically significant performance differences are identified using the appropriate test statistics. It is found that both the LS-SVM and neural network classifiers yield a very good performance, but also simple classifiers such as logistic regression and linear discriminant analysis perform very well for credit scoring
MEASURING GERMANY’S ECONOMIC INTEGRATION: A STATISTICAL APPROACH
No full textThis thesis measured the degree of economic integration of the reunified German states
for the period between 1991 and 2011 by using the statistical method developed by Bowen, Munandar
and Viaene. This approach is based on three theoretical predictions with respect to the distribution of
output and production factors across the member states of an integrated economic area (IEA), where
there are no barriers to goods and factor movements and policies are harmonized. Empirical results
show that all predictions hold and that the distribution human capital is the furthest away from the
theoretically expected one. The applied integration statistic indicates that during the covered period
Germany became more economically integrated, however integration stagnated since 1999. A further
East-West migration of higher educated is expected, but could be reduced through policy
harmonization. Also the union of Bremen and Saarland with their circumambient states will lead to a
distribution of human capital in Germany that is closer to what is theoretically expected
Predictors and Dynamics of the Humoral and Cellular Immune Response to SARS-CoV-2 mRNA Vaccines in Hemodialysis Patients: A Multicenter Observational Study
No full textBackground Preliminary evidence suggests patients on hemodialysis have a blunted early serological response to SARS-CoV-2 vaccination. Optimizing the vaccination strategy in this population requires a thorough understanding of predictors and dynamics of humoral and cellular immune responses to differentSARS-CoV-2 vaccines.Methods This prospective multicenter study of 543 patients on hemodialysis and 75 healthy volunteers evaluated the immune responses at 4 or 5 weeks and 8 or 9 weeks after administration of the BNT162b2or mRNA-1273 vaccine, respectively. We assessed antiSARS-CoV-2 spike antibodies and T cell responses by IFN-? secretion of peripheral blood lymphocytes upon SARS-CoV-2 glycoprotein stimulation (QuantiFERON assay) and evaluated potential predictors of the responses.Results Compared with healthy volunteers, patients on hemodialysis had an incomplete, delayed humoral immune response and a blunted cellular immune response. Geometric mean antibody titers at both timepoints were significantly greater in patients vaccinated with mRNA-1273 versus BNT162b2, and a larger proportion of them achieved the threshold of 4160 AU/ml, corresponding with high neutralizing antibody titers in vitro(53.6% versus 31.8% at 8 or 9 weeks, P Conclusions The mRNA-1273 vaccine's greater immunogenicity may be related to its higher mRNA dose. This suggests a high-dose vaccine might improve the impaired immune response to SARS-CoV-2 vaccination in patients on hemodialysis.This research was supported by Amgen (DONATION-331036).
A. De Vriese and J. Van Praet designed the study; R. Caluw e, A. De Bel, A. De Vriese, P. Doubel, L. Heylen, M. Schoutteten, J. Van Praet, B. Van Vlem, and L. Viaene provided study materials or patients; D. De Bacquer, A. De Vriese, M. Reynders, and J. Van Praet analyzed the data; D. De Bacquer and J. Van Praet made the figures; A. De Vriese drafted the paper; D. De Bacquer, M. Reynders, and J. Van Praet revised it critically for important intellectual content; all authors approved the final version
of the manuscript. The authors are indebted to Tessa Acke, Manuela Caster, Evelyne Deglorie, Mirjam Demesmaecker, Suzanne Driessens, Inne Hoebrekx, Annelien Leunen, Carine Lowis, Isabel Moyaert, Danny Pauwels, Joris Penders, Melissa Renders, Carmen Reynders, Sofie Tombeur, Katrien Uyttersprot, Femke Van Den Berg, Kristel Van Varenbergh, Tine Verheyen, Manon Verhulst, and Sophie Vleeschouwers for their invaluable help in the collection of the patient data and analysis of the samples
- …
