Todd Pleune

As a leader in Protiviti’s Risk and Compliance Analytics solution, Todd focuses on risk modeling and model validation for Credit Risk, Conduct, Operational, and Market Risk. He has developed model governance processes and risk quantification processes for the world’s largest financial institutions and is an SME for internal audit of the model risk management function. Todd developed Artificial Neural Network models for his Ph.D. work and has validated recently developed machine learning credit risk models. Todd has a Ph.D. in corrosion modeling from the Massachusetts Institute of Technology, where he minored in Finance at the Sloan School of Management and in Nuclear Physics including stochastic modeling.

Major Projects

• Internal audit SME for model risk management and valuation, risk, and stress testing model reviews. Evaluated model risk management for large and mid-size banks. Documented issues with model risk management, credit risk modeling and operational risk modeling. 
• Led model validations for credit underwriting developed used machine learning techniques, including Gradient Boosting Machine (GBM) and XGBoost for several banks and fintechs. 
• Conducted model validation and model development work for stress testing models for Operational Risk, Pre-Provision Net Revenue, Credit Risk and other models at several major banks. Validation issues were noted with certain models requiring model updates prior to submission to the Federal Reserve Board for the CCAR exercise. For development projects, evaluated correlation between economic and bank-specific input variables and risk metrics to develop models for stress testing. 
• Credit risk model validation experience includes PD LGD models, Allowance for Loan and Lease Losses (ALLL), Current Expected Credit Loss (CECL), scorecard models, Other than Temporary Impairment (OTTI), machine learning, economic capital, and others. Tested scorecards and regression models to evaluate the soundness of modeling techniques and the performance and stability of the resulting models. 
• Led Anti-Money Laundering model validation work testing transaction monitoring, customer risk rating, and sanctions screening for several banks of all sizes (community banks to large international banks). Evaluated data quality, assumptions and technical implementation to determine model effectiveness. Validated Fiserve FCRM, Actimise, D&H PAYPlus, Prime, Mantis, Abrigo (Bankers Toolbox) BAM+, Verafin, CSI WatchDOG Elite, LexisNexis Bridger Insight XG System, Fircosoft’s FircoContinuity System, and others. 
• Led fair lending statistical analysis projects to identify apparent fair lending risks and assess. Determined where consumer portfolios had demonstrated risk and recommended comparative file analysis where appropriate. 
• Led several Interest Rate Risk and Asset Liability Management model validation reviews for several wholesale and retail banks. Reviews include pricing for all types of assets and derivatives and assessed how the IRR model predicted actual bank results and sensitivity to changes in assumptions.

Areas of Expertise

• Model Validation
• Machine Learning
• Conduct Risk (AML and Fair Lending)
• Credit Risk
• Market Risk
• Operational Risk

Industry Expertise

• Financial Services 
• Energy

Education

• Ph.D. in Corrosion Modeling, MIT
• Minor in Finance, MIT Sloan
• B.S. Nuclear Engineering, University of Illinois

Professional Memberships and Certifications

• Financial Risk Manager – Certified by the Global Association of Risk Professionals
• Risk Management Association