Big Data

Model Risk Management

Banks routinely use models for a broad range of activities, including underwriting credit; valuing exposures, instruments, and positions; measuring risk; managing and safeguarding client assets; and determining capital and reserve adequacy. Models can improve business decisions, but they also impose costs, including the potential for adverse consequences from decisions based on models that are either incorrect or misused. Banks must objectively assess model risk using a sound model validation process, including evaluation of conceptual soundness, ongoing monitoring, and outcomes analysis. 

Our Model Risk management solution provides the following capabilities to enable Banks to manage their Model risk

  • Digital inventory for all your models with validation history
  • Manage a model through its lifecycle – from inception to retirement
  • One-click process to revalidate all your models
  • Support for multiple model types such as Scorecards, Binned Logistic, Logistics Regression Decision Tree/ Segmentation models ML models Linear Regression Judgmental
  • Multiple Metrics & Tests including
    • Model health assessment: PSI, KS, IV, Gini, Lift, Pietra, AUROC
    • Variable Health Analysis: CSI, VDI, IV Change
    • Calibration Tests: Binomial, Taasche, Score to Log-odds