Model Risk Validation Role - Credit Risk

Credit Risk Modeling:

Strong experience and practical in-depth understanding of Credit risk model development-validation methodologies and procedures.

Quantitative Background:

Strong quantitative background in Applied Statistics-Mathematics-Operations Research-Economics-Engineering-or related quantitative field.

Regulatory Regimes:

Strong work experience and practical understanding of at least one or more of the following regulatory regimes: US (FRB-OCC), UK (PRA-ECB), CBUAE (MENA), RBI (India), MAS (Singapore), HKMA (Hong Kong).

Credit Risk Models:

Strong work experience and-or in-depth practical understanding of Credit Risk models - PD (Probability of Default), EAD (Exposure in Default), LGD (Loss Given Default) models from either model development or model validation standpoint.

Statistical Modeling:

Sound work experience and good practical understanding of Statistical modeling techniques of Linear Regression, Logistic Regression; Machine learning approaches of Gradient Boosting (GBM), XGboost (Extreme Gradient Boosting), Cat-Boosting, and Random Forest. Time Series modeling knowledge approaches - ARIMA, ARIMAX would be added plus.

Programming Proficiency:

Highly proficient in statistical tools- programming languages (viz. Python, SAS, SQL, R).

Data Analysis:

Strong Experience with data analysis, data visualization, and data mining techniques.

Report Writing:

High quality Report writing skills from either Model Development or Model Validation perspective factoring the regional regulatory guidelines-framework and Standard Operating Procedures.

Critical Reasoning:

Strong Critical reasoning skills and analytical capabilities for analyzing models and related modeling-Financial products analysis and exercises.

Stakeholder Management:

Adept in Stakeholder Management and excellent in Oral and written communication skills as well as interpersonal skills.

Responsibility Areas:

• In-depth and End to End Validation of Credit risk models using both classical statistical techniques and machine learning approaches. Models span various Businesses of the Bank including Consumer Finance, Personal loans, Mortgages, Micro-Finance, Small Business Banking, Credit Cards, Corporate Banking, etc. and include both Acquisition and Behavioral score cards as well.
• Collect and analyze large datasets to calibrate and validate credit risk models.
• Evaluate the creditworthiness of Clients-Businesses and predict potential losses.
• Collaborate with cross-functional teams - FLoD (Model Developers, Model Owners, Risk, Businesses), Bureau teams, etc. to opine on the utility of the credit risk models in business decision-making processes.
• Staying up-to-date with Banking industry trends and Global-Regional as well as Local regulatory requirements.