MANAGER, MODEL GOVERNANCE

Responsibilities

• Provide hands on model governance oversight in development of new models or modifications to existing models used for across the customer credit lifecycle, i.e. marketing through servicing. Closely partner with data science team and provide guidance on leading model risk management practices.
  
• Perform independent challenges of models and identifies model weaknesses and opportunities for improvement. Evaluate and opine of major model building milestones, including but not limited to, target construction, choice of train vs. validate time period, sampling, performance time windows, parameter tuning routines, model metrics, variable selection and suitability, and swap set analysis.
• Build challenger models on select models as needed
• Ensure that modeling specifications and constructs adhere to defined mathematical and statistical standards
  
• Perform model validations on a periodic basis and evaluate whether validations and other reviews performed by the model governance team, business or third parties follow the requirements set forth in the MRM Policy.
• Uses analytics, business rules, and/or other risk tools and techniques to detect model behaviors and risk factors that may indicate activity that warrants further investigation or action.
  
• Prepares and distributes regular MIS reporting concerning risk monitoring activities. Effectively communicate outcomes of model risk management.
  

Qualifications:

• Masters in a quantitative field such as Statistics, Mathematics, Data Science, Computer Science, or related quantitative field.
  
• Advanced knowledge of statistical and machine learning methods, techniques, formulas, and tests.
  
• 5 years progressive experience in consumer credit industry
  
• 3 years of progressive experience in Model Risk Management
• Solid knowledge of key econometric and statistical techniques (i.e., predictive modeling, various regressions, decision trees, and data mining methods). Strong theoretical and applied background in Machine learning models, specifically tree based models like XGBoost.
• Familiarity with Large Language Models (LLM) desired

• Strong analytical, data, problem-solving and decision-making skills with high attention to detail and accuracy.
• Excellent presentation and communication skills, including technical writing abilities.
  
• Strong ability to communicate effectively with colleagues with varying degrees of technical analytics knowledge and experience.
  
• Strong problem-solving skills
  
• Strong idea generation and deep-thinking skills with interest in R & D
• Proficient in SQL, Python and MS office suite.