Data Scientist

Who we are:

Financeit is a point-of-sale financing provider serving some of the largest home improvement and retail organizations in Canada. Our platform helps businesses close more sales by offering customers affordable monthly payment options for their next big home improvement, vehicle or retail purchase.

We are small enough that you can make an impact within the company and large enough to make an impact in the market. Financeit is a company where collaboration, inclusivity, fairness, and respect aren’t just ideas that get talked about, but are part of who we are. If such a workplace intrigues you, we hope you’ll join us.

About the role:

Do you love diving into data, solving complex problems with tech, and figuring out what really drives credit risk and customer behaviour? Are you equally skilled at balancing deep analytical thinking with pragmatic execution, and always delivering on time? If you’re ready to take your data science, advanced analytic skills, and knack for digging into the details to the next level, while leaving your mark on a rapidly growing organization, we want to hear from you!

We are seeking a Data Scientist, Risk Analytics & Modeling, to work under the direction of the Director - Risk Analytics, Data Science & Reporting to develop and deliver robust risk machine learning and statistical models that support better credit decision-making, portfolio management, and risk measurement. You will play a key role in developing IFRS 9 models, behavioural models, and other predictive risk solutions, while building new modelling capabilities, operationalising and automating analytical processes, and turning complex data into actionable insights for stakeholders across the business.

Building models that are technically sound, commercially useful, and scalable is no small feat and requires a ton of team-based continuous improvement — especially when there’s always another process to automate, model to improve, or interesting dataset to play with.

What you’ll be doing:

• Build, validate, and refine sophisticated risk machine learning and statistical models across consumer credit, fraud, portfolio risk, and borrower behaviour
• Develop and enhance IFRS 9 models, including expected credit loss, probability of default, loss given default, exposure at default, and related risk forecasting and segmentation methodologies
• Build behavioural and predictive models that leverage customer, transaction, portfolio, and macroeconomic data to better understand and predict borrower behaviour and credit outcomes
• Go beyond the surface level to build sophisticated yet explainable models that connect data to real-world events, customer attitudes and behaviors to deliver insights and inform high-value business decisions
• Translate complex analytical problems into scalable modelling solutions, while balancing statistical rigour, interpretability, business impact, and practical implementation