Model Maestro

Purpose: predictive analytics and scoring
models development.

Banks need Scorto™ Model Maestro to perform credit risk models and scorecards development in-house as well as statistically analyze credit portfolios.

Concept and Key Tasks

• Analyzing credit portfolio data, visualizing customer characteristics distributions and dependencies with 3D reports, associative strengths, and Kohonen map
• Identifying the key factors, impacting customer’s creditworthiness
• Building scoring models with either logistic regression, decision tree/decision rules or neural networks, as well as creating expert scorecards
• Comparing different scorecards and analyzing their efficiency with ROC, Lorenz, Kolmogorov-Smirnov curves and many more popular model performance reports
• Processing imported data in order to detect and block anomalies, such as outliers, wrong type or missing values
  Connects to any database, including direct access to MS SQL and Oracle

Value Proposition

• Model Maestro demystifies the high science of scorecard development algorithms, brings it down to bank’s practical needs, with standardized pre-defined development flow and wizard-based interface
• Designed to be used by ordinary risk managers, predictive analysts and scorecard developers without Ph.D. background or strong mathematical skills. No need to learn the command-line language, everything is visual, best practices are incorporated into the standardized workflow
• With Model Maestro will have the power to create scorecards in-house, keeping all the knowledge and control inside an organization, without the need to transfer sensitive customer data to 3rd party scorecard developers or consultants
• Model Maestro supports the whole cycle of scorecard usage from cradle to grave. It gives ability not only to create but monitor and improve scorecards with pre-defined extremely visualized reports facilitating fast adaptation to changing market conditions
• Basel 2 ready: allows creating PD models with one click