This project aims to develop a robust foundation model designed explicitly for financial time series representation learning. The core of this approach is an autoencoder framework capable of capturing multi-modal relationships in financial data. Once trained, the encoder will be deployed as a general-purpose model for various downstream financial tasks, including predictive analytics and asset […]

This project will investigate new methods for improving decision-making tools that help organizations make better choices when faced with uncertainty. Specifically, we will study how to more accurately estimate weights in the Analytic Hierarchy Process (AHP), a common tool used for Multi-Criteria Decision Making (MCDM). By focusing on interval and fuzzy weight estimation, the project […]

(1) The Desjardins Quantitative Strategies department manages a set of internally developed systematic investment strategies. There are two main products; global equity strategies (developed and emerging countries), as well as alternative strategies using futures on global stock indices, resources, interest rates and currencies. The team owns a proprietary technology platform that has been developed over […]

This proposal aims to integrate mathematical analysis with numerical simulations using Physics-Informed Neural Network (PINN) schemes to investigate the primitive equations, a fundamental model for atmospheric and geophysical flows. The primary focus is on achieving a precise characterization of singularity formation in these models.

HIV-1 remains a global health challenge, with over 35 million people infected. The high rates of turnover and evolutionary adaptability exhibited by HIV-1 pose a particular challenge to the use of antiretrovirals, as well as the development of a vaccine. Our focus is to understand the dynamics of two of the most commonly tracked clinical […]

This research project focuses on using advanced machine learning techniques to better predict stock prices, specifically targeting stocks from the S&P 500. By combining powerful deep learning methods—such as LSTM and GRU networks—with adaptive attention mechanisms inspired by Transformer models, the project aims to create forecasting systems that can dynamically adapt to changing market conditions, […]

Awesense is a clean tech company on a mission to accelerate the transition to clean energy by simplifying the creation of data-driven applications for a decarbonized, decentralized grid. To enable the complex planning and operational decisions required by distributed energy resources (e.g., solar, wind, batteries, EVs), Awesense developed its Digital Energy Platform. This platform allows […]

Cancer treatment requires a precise understanding of how drugs work at different doses and schedules. This research project aims to develop an advanced method for designing clinical trials for early-stage cancer beyond traditional approaches. The project will create a sophisticated statistical framework that simultaneously evaluates drug toxicity and effectiveness across multiple complexity levels while incorporating […]

L’une des stratégies mise en oeuvre par Hydro-Québec pour accompagner la demande croissante d’électricité, consiste à caractériser les phénomènes contribuant à la dégradation des turbines hydrauliques. Dans cette optique, le phénomène de cavitation est étudié, car il est à l’origine de l’érosion et donc de l’endommagement des turbines. Ce phénomène correspond au passage de l’eau […]

This project explores the relationship between twisted traces on K-theoretic Coulomb branches, vertex functions of quasi-maps, and vertex operator algebra characters. Twisted traces provide a framework to understand quantum algebras and their symmetries, with potential applications in representation theory, mathematical physics, and geometry. The project aims to establish new connections between these areas, benefiting participating […]

Ce stage vise à porter un regard nouveau sur la modélisation du processus de réserve en assurance et gestion de risque financier en proposant une approche probabiliste basée sur les théories des équations différentielles stochastiques et le gradient stochastique. Ce cadre a été appliqué avec succès à de nombreux domaines de la modélisation mathématique. Notre […]

This project is to further Finliti’s proprietary behavioral science-backed trading algorithms by creating and analyzing data models. This will also provide the basis for quantifying the value proposition of specialized financial advice and education at scale for the wealth management landscape in Canada to direct Finliti’s growth and competitive advantage in the market place. Finliti […]