Analytics Scientist

Ford • Dearborn, MI

2d

About The Position

Research, develop, validate, and implement advanced statistical and quantitative models for credit loss forecasting (PD, LGD, EAD) at various levels of granularity (e.g., segment, portfolio). Explore, evaluate, and apply innovative modeling techniques, including machine learning and artificial intelligence methods, alongside traditional econometric and statistical approaches. Analyze complex credit performance data, portfolio characteristics, and macroeconomic trends from diverse data sources and platforms. Enhance and maintain existing credit loss models throughout their lifecycle, ensuring performance, stability, and adherence to model governance standards. Collaborate closely with partners in Risk Management, Finance, Accounting, and other business units to understand modeling needs, communicate model capabilities and limitations, and explain forecasting results. Translate complex quantitative analyses, modeling methodologies, and results into clear, concise, and actionable insights for both technical and non-technical audiences, including senior leadership. Support regulatory requirements related to credit loss forecasting, such as ECL/CECL (Expected Credit Loss/Current Expected Credit Loss) and stress testing, by ensuring model soundness and comprehensive documentation. Conduct ad-hoc quantitative analysis to support portfolio performance monitoring, risk assessment, and strategic initiatives. Develop and maintain comprehensive model documentation in accordance with internal policies and regulatory expectations. Established and active employee resource groups Master's degree in a quantitative field such as Statistics, Economics, Mathematics, Operations Research, Data Science, Computer Science or a related discipline. Demonstrated experience in developing and implementing statistical or quantitative models, preferably in a financial services or credit risk environment. Strong proficiency in traditional statistical modeling techniques (e.g., linear and non-linear regression, time series analysis, panel data models, survival analysis, multivariate techniques). Proven knowledge of Machine Learning and Artificial Intelligence concepts and techniques relevant to quantitative modeling problems (e.g., classification, regression, time series forecasting with ML/AI methods). Experience with statistical modeling software (e.g., SAS is highly preferred; proficiency in Python or R with relevant statistical/ML libraries is also valuable). Experience querying and manipulating large datasets using SQL. Solid analytical, problem-solving, and creative thinking skills with the ability to formulate problems and propose innovative solutions. Excellent written and verbal communication skills, with the ability to effectively translate complex quantitative concepts into business terms.

Requirements

• Master's degree in a quantitative field such as Statistics, Economics, Mathematics, Operations Research, Data Science, Computer Science or a related discipline.
• Demonstrated experience in developing and implementing statistical or quantitative models, preferably in a financial services or credit risk environment.
• Strong proficiency in traditional statistical modeling techniques (e.g., linear and non-linear regression, time series analysis, panel data models, survival analysis, multivariate techniques).
• Proven knowledge of Machine Learning and Artificial Intelligence concepts and techniques relevant to quantitative modeling problems (e.g., classification, regression, time series forecasting with ML/AI methods).
• Experience with statistical modeling software (e.g., SAS is highly preferred; proficiency in Python or R with relevant statistical/ML libraries is also valuable).
• Experience querying and manipulating large datasets using SQL.
• Solid analytical, problem-solving, and creative thinking skills with the ability to formulate problems and propose innovative solutions.
• Excellent written and verbal communication skills, with the ability to effectively translate complex quantitative concepts into business terms.

Nice To Haves

• Experience specifically in auto finance or banking credit risk modeling (PD, LGD, EAD).
• Experience with model validation processes, model governance, and regulatory requirements (e.g., CECL, stress testing).
• Experience applying specific ML/AI algorithms (e.g., Gradient Boosting Machines, Neural Networks, Ensemble Methods) to credit risk or time series forecasting.
• Experience with data visualization tools (e.g., Qlik sense, Tableau, Power BI, Alteryx).
• Experience working with large-scale data platforms (e.g., Google cloud platform or other cloud-based data warehouses).
• Highly analytical, detail-oriented, and intellectually curious.
• Ability to work independently with minimal supervision and manage multiple projects simultaneously.
• Proactive, team-oriented, and open-minded with a strong desire to learn and adapt to new techniques.
• Strong collaboration skills and ability to build relationships with cross-functional partners.

Responsibilities

• Research, develop, validate, and implement advanced statistical and quantitative models for credit loss forecasting (PD, LGD, EAD) at various levels of granularity (e.g., segment, portfolio).
• Explore, evaluate, and apply innovative modeling techniques, including machine learning and artificial intelligence methods, alongside traditional econometric and statistical approaches.
• Analyze complex credit performance data, portfolio characteristics, and macroeconomic trends from diverse data sources and platforms.
• Enhance and maintain existing credit loss models throughout their lifecycle, ensuring performance, stability, and adherence to model governance standards.
• Collaborate closely with partners in Risk Management, Finance, Accounting, and other business units to understand modeling needs, communicate model capabilities and limitations, and explain forecasting results.
• Translate complex quantitative analyses, modeling methodologies, and results into clear, concise, and actionable insights for both technical and non-technical audiences, including senior leadership.
• Support regulatory requirements related to credit loss forecasting, such as ECL/CECL (Expected Credit Loss/Current Expected Credit Loss) and stress testing, by ensuring model soundness and comprehensive documentation.
• Conduct ad-hoc quantitative analysis to support portfolio performance monitoring, risk assessment, and strategic initiatives.
• Develop and maintain comprehensive model documentation in accordance with internal policies and regulatory expectations.

What This Job Offers

• Job Type: Full-time
• Career Level: Mid Level
• Number of Employees: 5,001-10,000 employees