Quantitative Analytics Manager- Model Risk

Location: 127 Public Square, Cleveland Ohio

The Quantitative Analytics Manager is primarily responsible for leading the validation of predictive and machine‑learning models for specific business needs using statistics, advanced mathematical techniques, and/or computer science. The Quantitative Analytics Manager leverages advanced mathematical knowledge, analysis, partnerships, and business knowledge to provide solutions to predictive and prescriptive questions such as "What will happen next?" and "What will we do?". Projects undertaken are often broad in scope across multiple business segments and involve guiding a team and/or project through providing solutions to business problems leveraging statistics, best practices or emerging techniques, and quantitative tools / techniques.

Success factors include:
Demonstrating leadership through strong communication skills, addressing conflict, coaching others on developing technical skills; managing competing priorities and presenting holistic, thoughtful analyses to answer partners' problem statements; prioritizing multiple projects and managing to tight deadlines; establishing reputation as an effective and collaborative partner;
Communicating technical theories, observations, and models to a non-technical audience;
Leveraging knowledge of strategy, business, and competition to connect day‑to‑day work of team to the "bigger picture" and driving efficiency in solution delivery.

• Independently assess and validate models, inferential methodologies, and analytical frameworks to evaluate their appropriateness, robustness, and effectiveness in addressing business needs and ensuring reliable answers to "What will happen and how confident are we in the results", including CECL, Stress Testing, and Consumer/Commercial Credit Risk models
• Often responsible for large, complex problems that have broad implications and are less frequent
• Identify and articulate observations based on a structured assessment of context, interdependencies, and analytical outcomes, and evaluate their impact on model soundness, reliability, and business use Reviews deliverables; proactively coaches others on approach and work product
• Assess and challenge data preparation practices against established standards and model requirements, engage with data stewards to review data quality, traceability, and efficiency from a validation perspective
• Evaluate the appropriateness of analytical methods used and assess whether they are suitable and well justified for the given context

• Master's degree (or equivalent) in statistics, mathematics, economics, financial engineering, data sciences, predictive modeling, or other quantitative disciplines and at least 5 years of relevant experience; or Bachelor's degree (or its equivalent) in statistics, mathematics, economics, financial engineering, data sciences, predictive modeling, or other quantitative disciplines and at least 6 years of relevant experience

• Understanding of:
  • Best practices for capturing / retaining data
  • Pros / Cons of competing analysis methods
• Experience leading by:
  • Partnering with others to anticipate and understand needs process/procedures
  • Leading information practices / policies / procedures
  • Setting standards and expectations for data analysis tools and techniques; ensuring compliance with application
  • Promoting increased efficiency of data analysis by advocating clearer data requirements

• Advanced modeling techniques, including machine learning methods (e.g., XGBoost, Light
  
  GBM, Random Forest), with the ability to evaluate, challenge, and validate model design, tuning approaches, and performance testing
• Advanced Microsoft Office Suite
• SQL/No
  
  SQL
  • Relationship data structure
  • Selecting and retrieving data including unstructured data retrieval, archival, and ETL
  • Databases
• Advanced Python/R/SAS
  • Databases
  • Efficient coding
  • Can build strong code controls and translate code into high‑level commentary
• Understanding of and ability to leverage:
  • Cloud-based computing
  • Distributed computing

• Ability to:
  • Establish standards and best practices; forecast future modeling…