Modeling Default Risk for a Small Lender using Machine Learning

Individuals with limited or poor credit history are often unable to access credit from traditional sources such as banks. While some alternative lenders will provide credit to such individuals, these lenders typically lack reliable sources of information which can be used to accurately assess the risk that the loans they make will not be repaid, […]

Read More
L’intelligence artificielle au service de l’industrie de l’assurance

L’évolution technologique révolutionne les processus administratifs dans les banques et les assurances, mais entraîne également de nouveaux défis, en particulier au niveau de la reconnaissance de l’écriture manuscrite et imprimée dans les documents qui doivent être numérisés pour extraire automatiquement l’information pertinente. Les systèmes de dialogues automatisés connaissent également un succès grandissant, grâce à l’utilisation […]

Read More
Equivariant Siamese Neural Networks

The world we live in is ripe with symmetry. From the bilateral symmetry we see in humans to the symmetries which are used to describe fundamental particles in physics. Most modern machine learning methods however do not have an inherent modeling of symmetry in them. By developing algorithms which do have an explicit modeling of […]

Read More
Uncertainty Quantification for Deep Neural Networks

Deep neural networks are effective at image classification and other types of predictive tasks, achieving higher accuracy than conventional machine learning methods. However, unlike these other methods, the predictions are less interpretable. While accuracy may be enough for applications where errors are not costly, for real world applications, we want to also know when the […]

Read More
Predicting the Behavior of Loyalty Programs Customers Using Interpretable Patterns Based on Logical Analysis of Data

Aeroplan Inc. (“Aeroplan”) , aims to redesign and optimize its loyalty program Aeroplan via a collaboration with Polytechnique Montréal. Customers affiliated with Aeroplan’s program earn miles through their purchases and can exchange these miles for various gifts. It is essential for Aeroplan to predict customers behavior, to define the causes of certain behaviors and to […]

Read More
Inférence causale pour mesurer le retour sur les investissements publicitaires

Même si les compagnies d’assurances investissent des sommes considérables en publicité, il leur est souvent difficile, voire impossible, de répondre précisément et avec confiance à la question « Combien de nouvelles soumissions d’assurances par des clients potentiels sont générées grâce à ces investissements publicitaires ? » Pourtant, des données sur les efforts publicitaires et les […]

Read More
Changing Waters: Modeling Long-Term Fluxes of Phosphorus Under Changing Climate and Land Use in the North American Great Lakes Region

Participation in Mitacs Globalink will allow me to travel to Leipzig, Germany to pursue research at the Helmholtz-Centre for Environmental Research (UFZ). I will be working there as an undergraduate researcher within the Department of Computational Hydrosystems directly under Dr. Sabine Attinger. The aim of my project will be to learn and apply their mHM […]

Read More
Rationality problems

Algebraic geometry is the study of algebraic varieties, geometric shapes that arise as solution sets to systems of polynomial equations. Algebraic geometry is a subject of central importance in contemporary mathematics, with multiple connections to other areas, such as number theory, combinatorics, representation theory, analysis, and theoretical physics. The simplest algebraic varieties are rational varieties. […]

Read More
The Epidemiology of Fabry Disease and Metabolic Acidosis in Manitoba

The proposed project is for the postdoctoral fellow to access healthcare data for individual adults in the province of Manitoba in order to: 1) determine the rates of metabolic acidosis in Manitoba along with associated outcomes and risk factor profiles and 2) identify patients in Manitoba who are at high risk of Fabry disease but […]

Read More
Ré-optimisation en temps réel pour la réfection de navires

La planification de la réfection d’un navire est une tâche difficile qui requiert un effort considérable en termes de ressources qu’il faut gérer. Elle comprend plusieurs centaines d’activités d’inspection, de désassemblage, de réparation, de remplacement, de reconversion, de modernisation et de réassemblage. De plus, il faut prendre en compte les contraintes d’espace qui limitent le […]

Read More
Twisted foldings and double moment graphs

Schubert calculus is a well-established area of modern geometry that studies configurations and intersections of linear subspaces. Since its invention more than a century ago, it became one of the fundamental tools in different areas of mathematics, physics and computer science that deal with solving various types of linear equations. A typical question which is […]

Read More