Séance MB5 - Statistiques - exploitation de données / Statistics - Data Mining
Jour lundi, le 04 mai 2009 Salle Ordre des CGA Président Gilles Caporossi
Présentations
|
15h30- 15h55 |
Evaluation of Exponential Smoothing Models for Demand Forecasting with Combined Shewhart-CUSUM Control Charts |
|
Leandro C. Coelho, CIRRELT, HEC, Gestion des opérations et de la production, Université de Montréal, C.P. 6128, succursale Centre-ville, Montréal, QC, Canada, H3C 3J7 Robert W. Samohyl, Universidade Federal de Santa Catarina, Departamento de Engenharia de Produção, Florianópolis, SC, Brazil, 88040-970 We consider the problem of modeling the demand using exponential smoothing forecasts methods and to evaluate and control it using combined Shewhart-CUSUM control charts, with control limits calculated by simulation for this specific application. This control chart acts as an alarm for the need of re-estimation of the exponential smoothing model and its components. |
|
15h55- 16h20 |
Using Text Mining to Help in the Grant Evaluation Process at NSERC |
|
Franck Belot, GERAD, HEC Montréal, Méthodes Quantitatives de Gestion, 3000, chemin de la côte-ste-catherine, Montréal, Québec, Canada, H3T 2A7 Gilles Caporossi, GERAD, HEC Montréal, Méthodes quantitatives de gestion, 3000, chemin de la Côte-Sainte-Catherine, Montréal, Québec, Canada, H3T 2A7 Roland P. Malhamé, GERAD, École Polytechnique de Montréal, Génie électrique, C.P. 6079, Succ. Centre-ville, Montréal, Québec, Canada, H3C 3A7 The quality of the evaluation of grant applications is a paramount objective for Canada's NSERC (Natural Science and Engineering Research Council). It is therefore important that each application be reviewed by an adequate group of experts. In view of the growing trends of interdisciplinarity in research, the clustering of applications and assignment of the right group of experts to each cluster has become an increasingly difficult task. We attempt to take advantage of text mining in this clustering/expert assignment process. |
|
16h20- 16h45 |
Bankruptcy Predictions Using a Discrete-Time Survival Trees Approach |
|
Imad Bou-hamad, HEC Montréal, Méthodes quantitatives de gestion, 3000, chemin de la Côte-Sainte-Catherine, Montréal, Québec, Canada, H3T 2A7 Discrete-time survival data with time-varying covariates are often encountered in practice. One such example is bankruptcy studies where the status of each firm is available on a yearly basis. We apply a new survival tree method to a sample of United States firms that conducted an Initial Public Offerings between 1990 and 1999. |