Paige Stewart is a Toronto-based quantitative analyst currently working at a
multinational financial services firm. We spoke about her daily workflow, the
unpredictable nature of volatility analytics, and what she wishes she’d known when
starting out. Her perspective underscores how machine learning isn’t a shortcut, but
a challenge that requires constant rethinking.
Tell us about your typical day as a quantitative analyst working in volatility
forecasting?
My day starts with a brutal review of overnight data feeds. We run live
volatility forecasts across multiple asset classes—nothing gets spared the
early-morning reality check. If a model underperforms, I don’t blame the market.
I start by questioning our assumptions and whether the data even fits the logic
we used yesterday. It’s less about building something perfect, more about
finding out what broke and why. The field demands constant skepticism, not just
technical skills.
What are the highlights and challenges you face in your current role?
The highlight is when a model actually survives new data—most don’t. You spend
weeks tuning parameters, and then one real event wipes out your expected
volatility curve. That’s when the team comes together to diagnose what went
wrong, not to assign blame but to learn. The biggest challenge is getting
comfortable with uncertainty. The market doesn’t reward confidence, it punishes
overconfidence. You need a thick skin and a willingness to be wrong.
How does machine learning change the way you work compared to traditional
approaches?
It’s easy to get seduced by machine learning algorithms. They’re powerful but
can also hide mistakes better than traditional models. I spend a lot of time on
model explainability—why did the algorithm make that prediction? If I can’t
answer that, I don’t deploy it. We have technical reviews where everyone is
expected to find flaws, not just praise clever code.
What advice would you give to someone entering volatility analytics?
For someone new, I’d say forget about impressing with jargon. Focus on being
able to explain your process to someone outside the field. If your model only
makes sense to you, it probably doesn’t work. Accept that a lot of your work
will end up in the trash. That’s normal, and it’s how you get better.
How has your perspective on the field changed since you started?
Honestly, nothing prepares you for how quickly the field moves. What felt
advanced last year is already being replaced. The only constant is change and
the ability to adapt. We’re all still learning—and that’s the only part that
feels certain.
We use cookies and similar technologies to enhance site functionality, analyze
usage, and remember your preferences. For details, review our Cookie Policy or
adjust your settings below.
Essential cookies
Essential cookies are required for secure site access and basic functions.
Analytics cookies
Analytics cookies help us monitor usage and improve services. Data collected is
anonymized.
Marketing cookies
Marketing cookies may personalize content or advertising through trusted
partners.
