Quant Modeling [Multiple Positions Available]

JPMorgan Chase & Co.•Jersey City, NJ

6d•$188,178 - $215,000•Onsite

About The Position

This role involves driving the validation of forecasting models for the consumer lending portfolio, including CCAR and CECL models. It also includes validating all models used in the consumer lending portfolio, such as those for underwriting, pricing, collateral evaluations, collection, and recoveries. The position requires assessing consumer credit lending models by evaluating their conceptual soundness, assumptions, input reliability, and outcomes. Responsibilities include designing and executing tests for scenario analysis, loss forecasting, stability, and sensitivity of model components, and comparing model outputs to empirical evidence, industry benchmarks, and historical portfolio performance. The role also involves communicating validation results and model risk issues to various teams, preparing documentation for bank regulators, monitoring model performance, documenting findings, and recommending improvements. Maintaining and enhancing model risk controls, escalating issues, and assessing proposed resolutions are also key duties. The role requires applying SR 11-7 guidance on Model Risk Management and educating junior team members on model review best practices.

Requirements

PhD in Economics, Mathematics, Statistics, Data Science, Mathematical Finance, or related field of study plus 3 years of experience in the job offered or as Quant Modeling, Model Risk, Risk Advanced Analytics Specialist, or related occupation.
Alternatively, a Master's degree in Economics, Mathematics, Statistics, Data Science, Mathematical Finance, or related field of study plus 5 years of experience in the job offered or as Quant Modeling, Model Risk, Risk Advanced Analytics Specialist, or related occupation.
Developing or validating models for financial institutions including stress test models, allowance models, and models used in consumer retail lending.
Performing statistical analysis including logistic regression, multivariate regression, classification methods, cohort analysis, predictive modeling, quantitative analysis of time series and panel data using econometric methodologies and machine learning analysis including XGBoost, applied to consumer retail lending models.
Designing, developing, and automating model validation quantitative analysis for consumer lending stress test and consumer retail models using SAS and Python, including coding scripts to extract, analyze, and visualize model results with Python libraries including pandas, numpy, pyspark, scikit-learn, and statsmodels.
Reviewing model outputs, monitoring model performance, identifying model risk issues, and escalating findings for resolution in consumer lending.
Ensuring compliance with CCAR, CECL, and SR 11-7 model risk management standards during model validation and review as applied to consumer lending products.

Responsibilities

Drive validation of forecasting models for consumer lending portfolio including Comprehensive Capital Analysis and Review (CCAR) and Current Expected Credit Loss (CECL) models.
Drive validation of all models used in consumer lending portfolio such as underwriting, pricing, collateral evaluations, collection and recoveries.
Assess consumer credit lending models by evaluating conceptual soundness, assumptions, input reliability, and outcomes.
Design and execute tests for scenario analysis, loss forecasting, stability, and sensitivity for model components.
Compare model outputs to empirical evidence, industry benchmarks, and historical consumer lending portfolio performance.
Communicate validation results and model risk issues to Model Developers, Risk, Finance, Control teams, and Internal Audit.
Prepare the fact base for communication with Bank regulators.
Monitor model performance, document findings, and recommend improvements to ensure regulatory compliance and business relevance.
Maintain and enhance model risk controls for consumer lending, escalate issues, and assess proposed resolutions.
Apply SR 11-7: Guidance on Model Risk Management in all validation and governance activities.
Educate junior team members in model review best practices including how to conduct independent testing.