Financial stress can affect any Canadian, regardless of age, marriage status, or total wealth. At the Financial Wellness Lab (Western and Wilfrid Laurier Universities), we aim to develop methods to improve Canadians’ financial resiliency, reduce financial stress, and support better financial decision-making. We will explain how machine learning can be used to engineer financial behaviour metrics, investigate investor behaviours, understand if and how financial advice is being followed to characterize, and better understand common client trading personalities based on their behaviours and demographics.

We will discuss how client behaviours can be quantified using a modified behavioural finance recency, frequency, monetary model (RFM), and trading personality types can be elucidated using unsupervised and supervised clustering algorithms. Understanding the groupings of client behaviours enables financial advisors and dealerships to better understand how clients may behave during calm and turbulent market conditions based on their demographics and historic trading behaviours.

We will also discuss an empirical value-at-risk (VaR) methodology that quantifies risk using real market data. VaR can be used to measure and compare the difference between risk elicited by client questionnaires through advisor interpretation and risk revealed from trading behaviours through a portfolio. Notably, we show how VaR can be used to measure if a client is over-risked or under-risked, changes in KYC risk lead to changes in portfolio configuration, and cash flow affects a client’s portfolio risk. Lastly, and time permitting, we will discuss machine learning applications to understand financial stress and financial resilience using American and Canadian wellness survey data.