Risk Manager II (US)

TD•Southfield, MI

3d•$115,440 - $173,160•Onsite

About The Position

The Risk Manager II manages the creation, implementation and validation of various risk segmentation strategies including, but not limited to: adjudication, exposure management, risk segmentation, and financial return optimization. The position requires a strong statistical and mathematical background with auto lending experience; expertise in logistic regression, decision trees, clustering, survival analysis, GLM, gradient boosting, scorecard development, reject inference, PD/LGD loss prediction and machine learning. It also requires hands-on analytics experience with bureau and alternative data sources, and knowledge of feature engineering and attribute aggregation. Advanced proficiency in SAS, R, Python, and related analytical tools is necessary. The position is expected to integrate large, diverse datasets, apply feature engineering, and identify trends and patterns to support model development and enhancement. It will also develop and enhance scorecards and models throughout the credit life cycle using statistical methodologies and machine learning techniques, coordinate model deployment across FICO Decision Engine, Python, and related platforms, and partner with stakeholders to support Model Risk Management due diligence and timely issue resolution. The role will leverage statistical models and vendor data platforms to improve acquisition and portfolio performance, support downstream use of models, consolidate business impact analyses related to model or strategy changes, and communicate key findings to the management team. This role performs functions noted for Risk Manager I, is generally an expert at the enterprise or group business level, acts as the primary regulatory interface on risk issues and requirements for a key business segment of the Bank and assesses and provides direction for existing and new regulations. It interfaces with teams beyond risk in a cross-functional manner and represents the business on corporate initiatives, identifying key risks and implications and providing direction in complex situations.

Requirements

Strong statistical and mathematical background with auto lending experience; expertise in logistic regression, decision trees, clustering, survival analysis, GLM, gradient boosting, scorecard development, reject inference, PD/LGD loss prediction and machine learning.
Hands-on analytics experience with bureau and alternative data sources, and knowledge of feature engineering and attribute aggregation.
Advanced proficiency in SAS, R, Python, and related analytical tools.
Bachelor's degree required.
10+ years' experience required.
Proficient PC skills in MS Office and a variety of PC-based analytical and reporting software packages.
Experience with the use of Relational Databases and the process of Extract Transform Load (ETL) using common languages such as SQL or SAS.
Working knowledge of SAS Enterprise Miner, FICO Model Builder or Angoss Knowledge Seeker.
Strong analytical and problem solving skills are required to interpret data and draw conclusions.
Flexibility to adapt to rapidly changing requirements.
Extremely strong attention to detail with ability to manage a range of tasks and prioritize.
Proven ability to develop and maintain productive business/peer relationships.
Superb written and verbal communication skills.
Experienced in developing and presenting recommendations to Senior Management.

Nice To Haves

Graduate degree preferred or progressive work experience in addition to experience below.

Responsibilities

Manages the creation, implementation and validation of various risk segmentation strategies including, but not limited to: adjudication, exposure management, risk segmentation, and financial return optimization.
Integrate large, diverse datasets, apply feature engineering, and identify trends and patterns to support model development and enhancement.
Develop and enhance scorecards and models throughout credit life cycle using statistical methodologies and machine learning techniques.
Coordinate model deployment across FICO Decision Engine, Python, and related platforms.
Partner with stakeholders to support Model Risk Management due diligence and timely issue resolution.
Leverage statistical models and vendor data platforms, to improve acquisition and portfolio performance.
Support downstream use of models, consolidate business impact analyses related to model or strategy changes, and communicate key findings to the management team.
Acts as the primary regulatory interface on risk issues and requirements for a key business segment of the Bank and assesses and provides direction for existing and new regulations.
Represents business on corporate initiatives and identifies key risks and implications and provides direction in complex situations.