Manager, Loss Forecasting Models

BMO•Toronto, ON

2d•CA$82,800 - CA$154,800•Onsite

About The Position

The Manager, Loss Forecasting Models leads the development, enhancement, and governance of advanced forecasting models for retail credit portfolios. This role is highly technical and strategic, focused on applying statistical, machine learning, and AI methodologies to improve loss forecasting accuracy and business decision-making. The ideal candidate brings strong experience from leading financial institutions, deep quantitative expertise, and hands-on programming skills, along with the ability to lead model initiatives and collaborate with stakeholders across Canada and the U.S.

Requirements

Master’s degree or higher in a quantitative discipline (Statistics, Mathematics, Economics, Data Science, Engineering, Computer Science, or related field).
Minimum 5+ years of experience in credit risk modeling, loss forecasting, or quantitative analytics within a bank or financial institution.
Proven experience developing loss forecasting / credit risk models (e.g., PD, LGD, ECL, stress testing).
Strong hands-on expertise in Python, SAS, and SQL for data manipulation, modeling, and analysis.
Solid foundation in statistics, econometrics, and predictive modeling techniques.
Demonstrated experience applying machine learning and AI methods to improve model performance and forecasting outcomes.
Experience working with large-scale, complex datasets in banking environments.
Strong problem-solving skills and attention to detail.
Regulatory capital and stress testing.
Compliance and regulation.
Machine learning.
Learning Agility.
Systems Thinking.
Model risk management.
Data visualization.
Data wrangling.
Data preprocessing.
Critical thinking.
Driving Results.
Verbal & written communication skills.
Collaboration & team skills.
Analytical and problem solving skills.
Data driven decision making.
Quantitative financial modeling.
Computational thinking and programming.
Typically between 5 - 7 years of relevant experience and post-secondary degree in related field of study or an equivalent combination of education and experience.
Deep knowledge and technical proficiency gained through extensive education and business experience.

Nice To Haves

Prior experience at leading financial institutions or exposure to multiple banking environments.
Knowledge of IFRS 9 / CECL frameworks and macroeconomic scenario modeling.
Experience with model governance frameworks and regulatory expectations (e.g., SR 11‑7).
Leadership or mentoring experience in analytics or modeling teams.

Responsibilities

Lead the design, development, and implementation of loss forecasting models for retail credit portfolios.
Apply advanced statistical techniques and modern machine learning / AI approaches (e.g., GLMs, gradient boosting, random forests, neural networks) to enhance forecasting accuracy and risk insights.
Drive innovation by incorporating alternative data, new modeling techniques, and automation into forecasting frameworks.
Oversee the full model development lifecycle: data extraction, feature engineering, model training, validation, benchmarking, and deployment.
Ensure models comply with internal governance standards and regulatory expectations (e.g., SR 11‑7, IFRS 9 / CECL where applicable).
Lead the analysis of large, complex datasets from multiple sources using Python, SAS, and SQL.
Guide exploratory data analysis to identify trends, macroeconomic drivers, and emerging portfolio risks.
Promote best practices in coding, model reproducibility, and scalable analytics.
Implement automation and reusable solutions to streamline forecasting and reporting processes.
Oversee ongoing model monitoring, including PSI, KS, AR, calibration, and back-testing.
Identify model degradation, data drift, and performance gaps; recommend recalibration or redevelopment strategies.
Ensure robust monitoring frameworks are in place to support proactive risk management and regulatory compliance.
Partner with senior stakeholders across Risk, Finance, Product, Strategy, and Model Risk Management.
Translate complex modeling outputs into actionable business insights.
Support model validation and audit processes by providing clear documentation and analytical evidence.
Mentor junior analysts and provide technical guidance on modeling best practices.
Ensure comprehensive documentation of all models, including methodology, assumptions, limitations, and performance results.
Maintain high standards of model transparency, explainability, and regulatory compliance.
Lead responses to model validation, audit, and regulatory inquiries.