AI-based virtual assistant for the insurance industry

The insurance industry is a competitive sector that is expected to account for 3.1 percent of Canada's Gross Domestic Product in 2021. Leading insurers are investigating how machine learning (ML) may enhance company operations and customer satisfaction as clients become more selective about personalizing their insurance purchases to their particular needs. AI chatbots have the potential to significantly improve consumer satisfaction. Their primary goal is to assist consumers by answering questions.

Going Beyond Thin Credit, the use of Account Data

The business partner is interested in finding ways to further automate small business lending and annual renewals. In recent years, with the improvement in efficient computing and data storage and movement, the use of deposit data in lending has become more prevalent in the industry. Within industry risk managers, it is widely accepted that deposit account information has a strong predictive ability for predicting borrower risk level. However, there are no widespread industry tools similar to credit scores making use of deposit data.

Effective and Efficient Representation Learning and Inference for Sequential Data

Many problems in financial analysis planning, as well as, textural and visual processing, involve representing sequentially structured data (e.g., sequence of financial transactions, words in a sentence, etc.) computationally and making predictions based on these representations. The goal of this project is to explore fundamental strategies that improve such representations, both in terms of their ability to better model underlying trends and meaning in the data, as well as computational efficiency.

New Order of Risk Management: Theory and applications in the era of systemic risk (NORM)

To transform the way we think of and manage risk, in this research program we develop a comprehensive theory of systemic risk that combines the physical and social dimensions of risk, its spatial and temporal domains, and its primary and secondary channels of impact within a framework that acknowledges differences in risk vulnerability and susceptibility.

The barriers experienced by Alberta’s English-speaking immigrant Black Canadian entrepreneurs

Because Alberta is the largest growing population of economic-class Black immigrants from Africa, there is the potential for this population to contribute meaningfully to the Alberta’s economic prosperity and diversification. Because entrepreneurship is a preferred vocation for Canadian immigrants, this study aims to narrow down the entrepreneurial experiences of immigrant entrepreneurs from English-speaking Africa; particularly in Alberta’s innovation ecosystem.

An Interactive Dashboard for Human-AI Detection of Anomalous Employee Accounts at Risk of Data Exfiltration

Confidential data is one of the most precious assets large organizations can have and data theft can be embarrassing and costly. In this research we will carry out innovative research on detecting employee accounts that are exhibiting risky behaviour that may lead to leakage of data, whether carelessly or through malicious intent. It is difficult to protect against careless actions of employees, or malicious people masquerading as employees. Machine Learning (ML) models have been used to make identification of anomalous data transfers more efficient.

Managing tree models plasticity and mixing GLMs with regression trees for insurance ratemaking

Predicting policyholders' claims over a year is crucial for a Property-Casualty insurance company. These expenditures, popularly called losses, are incurred by the insurer when reimbursing the policyholders' claims. The insurance company is required to pay any legitimate claim made by a policyholder, in exchange the latter pays an amount of money, called the premium, to the company to buy this entitlement. Annual premium must be calculated with precision to ensure a fair deal on both sides.
It is the task of actuaries to set premiums for all policyholders; this is called ratemaking.

Complex Network Data Analysis for Systemic Risk Management and Loss Prevention

Financial fraud is a very serious problem plaguing financial institutions. Recent advances in information technology have only exacerbated this problem. Poor risk models were at the core of the 2008 financial crisis. Complex networks, structured graphs, are powerful models for representing higher-order interactions or dependencies within data sets. Graphs are relational models of covariates, where nodes represent variables and arcs their connections (relationships).

Effective Climate Governance for Canadian Credit Unions: Cooperating for a Greener Future

The goal is to develop a best practice guide for Canadian credit unions, focusing on the legal duties of Canadian directors and officers in respect of managing climate change, best practices for corporate boards, reporting on the latest global research on best climate governance practices for credit unions.

Advanced Quantitative Behavioral Models for Asset-Liability, Interest Rate Risk, and Liquidity Management in Deposit-Taking Financial Institutions

Cashflow uncertainty due to customer behaviors poses special challenges to a bank’s ability to accurately forecast its future cashflows, and therefore makes its funding and risk management difficult. In the proposed research, we plan to use cutting-edge machine learning techniques to study the behaviors of bank depositors and borrowers in Canada using an extensive proprietary data sample of the Partner Organization (i.e., EQ Bank).