India's largest platform and marketplace for AI & Analytics leaders & professionals

Sign in

India's largest platform and marketplace for AI & Analytics leaders & professionals

3AI Digital Library

Basel II Credit Risk Modeling

3AI August 17, 2020

A diversified global financial services company

Problem Statement

  • Compliance with Basel II regulations for Global Credit Card portfolio
  • Need consolidated exposure at the parent level for the segments–wholesale and retail
  • Existence of several versions of single model with virtually no documentation

Analytics Led Approach

  • Relevant data elements merged to create single version of truth for customer’s credit exposure
  • Multiple validation across different sources and different data granularity
  • Scenario analysis to finalize segments for model build
  • Developed probability of default models (PD) to score the entire institutional customer base in accordance with Basel 2 norms

Business Impact

  • 40% jump in ability of PD models to accurately capture ‘at risk’ customers
  • Effective credit portfolio management using the principle of risk adjusted return on capital
  • Timely compliance with the capital adequacy guidelines outlined by the Basel committee
  • Reduction in the overall regulatory capital charges due to better risk management

Critical Success Factors

  • Understanding of Basel II norms
  • Expertise in predictive modeling techniques (logistic regression, IV analysis, missing imputation, etc.)
  • Expertise in modeling tools and languages (SAS, SQL etc.)
  • Ability to embed compliance requirements into modeling parameters

    3AI Trending Articles

  • CES 2021 conference stress importance of security education

    Experts at the CES 2021 conference stress importance of security education The “second age” of quantum computing is poised to bring a wealth of new opportunities to the cybersecurity industry – but in order to take full advantage of these benefits, the skills gap must be closed. This was the takeaway of a discussion between […]

  • Can modern AI systems solve any problem on their own?

    Featured Article: Author: Puneet B C, Data Scientist – Computer Vision, AIRBUS First, let’s briefly understand what AI is. Artificial Intelligence is basically an algorithm or a rule that is used to make decisions automatically. Making a decision is to generate a desired output for the given input. In order to achieve this, the algorithm […]

  • Blockchain and IoT gives end-to-end visibility to Stakeholders in a Supply Chain

    While IoT sensors help track the movement and quality of products, blockchain’s distributed ledger gives multiple entities joint control over shared information . Covid concentrated attention on supply chains like never before as the pandemic caused massive disruptions. Companies started looking deeper into the roots of their supplies, going further back than their immediate vendors. […]

  • How Augmented Analytics is Transforming the Analytics Ecosystem

    Author:  Sidharth Sivasailam, Vice President – Products, Course5 Intelligence | LinkedIn – https://www.linkedin.com/in/sidharthsiva/ The world of Business Analytics is at an inflection point. Trillions of bytes of data are being generated every day; however, companies continue to struggle with harmonizing this data, analyzing the data of various shapes and sizes they are storing, determining what’s […]