Graph Feature-Engineering for Scalable Fraud Detection in Commercial Banking

The goal of the research project is to enhance ATB’s fraud detection by incorporating new graph based features. Initially, the project will be focused on figuring out how to use ATB’s data to build graph features. Once the data is processed, these additional graph variables will be used to improve the existing fraud detection machine […]

Read More
The fluid dynamics of expanding lava deltas

When lava enters the ocean, the molten rock spreads out and solidifies, creating a new shelf of land known as a lava delta. There have been a number of significant examples of such events over the last few years, notably at Kilauea, Hawaii in 2018, and Cumbre Vieja, La Palma in 2021. The physics of […]

Read More
An Investigation into Coupling a Stochastic Approximation with an Exotic Sampler

Algorithms that learn and sample from probability distributions form an important part of machine learning, AI, and the natural sciences. One needn’t look far to find such algorithms at the bleeding edge of methodology, and in everyday scientific pursuit. The Wang-Landau algorithm is an example. It combines a sampling step with a learning step, to […]

Read More
Conception d’un outil d’aide à la décision pour l’allocation optimale des espaces et la consolidation des cliniques ambulatoires de l’IUCPQ-UL

L’Institut universitaire de cardiologie et de pneumologie de Québec-Université Laval (IUCPQ-UL) est responsable du programme de soins et des services spécialisés et surspécialisés dans le traitement des maladies cardiovasculaires, respiratoires et en lien avec l’obésité, Afin d’accomplir cette mission, un ensemble de cliniques internes et externes (ou ambulatoires) sont rassemblées sous un même toit. La […]

Read More
Tests for models used in Actuarial and Risk management and Economic forecasting

In Actuarial Science and insurance, models are often used to assess risk using factors such as age, level of education, gender, environment, etc. In practice, there might be unobserved factors. When data are gathered, the accuracy of these models should be investigated. If the model is not well fitted by the data, subsequent influences could […]

Read More
Quantum Machine Learning for Doppler Radar Signal Processing in Clutter

Quantum computers are no longer fantasises of distant future. Recent advances in quantum computing hardware as well quantum algorithms offer a wide variety of possibilities to improve existing classical algorithms. Some of the operations involved in the standard classical algorithms might be performed much more efficiently using quantum machines. The current proposal will explore the […]

Read More
Programming Techniques for QUBO Compatible Processors

The main problem this internship project explores is the selection, conversion, and encoding of mathematical models that pertain to the finance industry for processing on available types of analog optimization processors. This research investigation aims to develop new algorithms and code that take advantage of an analog optimization process which acts as an “oracle” for […]

Read More
Exploration of Authoring Features to Facilitate Rapid Creation of STEM Subject Content in Mobile Practice Applications

This internship is a continuation of a previous Mitacs Accelerate Internship during which time Mathtoons worked with Dr. Wang of UBC Okanagan and intern, Yipin Guo of the Math and Computer Science faculties. The previous research enabled Mathtoons development team to incorporate many features within its Content Editor software which will allow teachers of upper […]

Read More
The Three-Body Problem, and the Great Inequality of Jupiter and Saturn

We propose to produce a self-contained analysis and reduction of the equations of motion of the much-studied three body problem, making application to the Great Inequality (GI) of Jupiter and Saturn. The GI is a result of the mutual gravitational attraction between these two planets. Their orbits are very nearly in resonance (integer ratio of […]

Read More
Consolidating High-Frequency and Textual Data for Optimal Anomaly Detection in Derivative Markets

In the last few years, a high increase in the interest of traders and investors towards financial instruments directly led to an important augmentation of the information received daily by exchanges. Exchange regulators, who constantly monitor markets to unveil potential infractions, traditionally perform their investigation manually and the notable growth in market activity represents an […]

Read More