Development of a Natural Language Processing algorithm for the topic and novelty identification of scientific articles

Currently the selection of peer reviewers is a secret process entirely controlled by journal editors. This introduces significant biases into the process that fosters an environment that contravenes every aspect of equity, diversity and inclusivity, inhibits novel ideas and suppresses creativity which is just bad for science as a whole. Furthermore, research is most often […]

Read More
Development of a risk-prediction model

A quantitative risk prediction model is to be constructed. We need to determine if the available data will fit an existing model and validate the results or if a new statistical model is required. Each case will be allocated into one of three categories (low, moderate and high risk). This stratification must have clinical validity […]

Read More
Structured Assets’ Value-at-Risk: Measurement and Sensitivity Testing

This project aims to measure the credit risk of Sun Life structured assets portfolio. The objective is to evaluate the accuracy of different methods to assess the credit risk of these types of financial instruments and to evaluate their advantages and limitations. Two methods are proposed to assess structured finance assets risk: Loan Equivalent Approach […]

Read More
Application of Machine Learning in Radiation Oncology Scheduling

Cancer incidence rates in Canada are increasing steadily every year which puts a strain on the treatment system. In Quebec, the waiting time to start treatment of cancer patients is enforced by law, however, it is difficult to meet with limited resources and personnel. Efficient planning is hence vital in reducing the long waiting time […]

Read More
Designing global event sets of floods and tropical cyclones under future climates for underwriting, capital management and regulatory purposes

With mounting pressure coming from regulators and other bodies worldwide, the financial services industry (banks, insurers, and reinsurers) will soon need to disclose and stress test their solvency and profitability to various climate scenarios. The work from the Task Force on Climate-related Financial Disclosures (TCFD) thus provides guidance as to how it should be accomplished. […]

Read More
Factorisation Matricielle Nonnégative rapide dans des espaces de Hilbert

La factorisation matricielle nonnégative (FMN) est une méthode populaire d’analyse de données consistant à exprimer les données comme une combinaison linéaire nonnégative d’un petit nombre de facteurs caractéristiques nonnégatifs. Cela permet de réduire la taille des données, de filtrer le bruit présent dans celles-ci et de mieux les comprendre et les analyser. Cette technique possède […]

Read More
Online Data Imputation by Modified Mixture Density Networks

In the era of big data, software based on artificial intelligence has greatly improved the quality of people’s lives. Although data is not a scarce resource, the data we collected are usually incomplete due to many reasons, i.e. they contain some missing values. Simply deleting these missing data will not only cause great waste, but […]

Read More
Fraud Detection in Derivatives Market using Graph Neural Network (GNN)

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
Équité et discrimination des modèles en assurance, un état de l’art

Historiquement, les primes d’assurance ont été ainsi différenciées à l’aide de quelques variables tarifaires, comme la surface de la maison en assurance habitation ou la puissance de la voiture en assurance automobile, mais aussi du genre ou de l’âge de l’assuré. Mais si la corrélation globale entre âge et coût du risque est indéniable dans […]

Read More
Discovering novel approaches to robust machine learning and visualization for banking applications

The overall objective of this project is to develop approaches to improve rating robustness that are distributionally robust. We will develop techniques to utilize ensemble learning machine learning models with categorical monotonic constraints. Lastly, we will develop novel data visualization tools for business intelligence tasks that will help decision makers at Scotia Bank.

Read More
Human Health Risk Assessment of Manganese and Inorganic Manganese Compounds and the Application of Categorical Regression in the Quantitative Risk Assessment of Manganese

Risk Sciences International is currently completing a comprehensive risk assessment of the potential human health effects of manganese. This assessment involves a systematic review of the worlds’ literature on epidemiological and toxicological studies of manganese, following which an international expert panel has scored all of the adverse health outcomes identified through this review using a […]

Read More