• Corpus ID: 211677672

Roughness Penalty for liquid Scorecards

  title={Roughness Penalty for liquid Scorecards},
  author={Bruce Hoadley},
  journal={arXiv: Methodology},
  • B. Hoadley
  • Published 1 March 2020
  • Mathematics
  • arXiv: Methodology
A liquid scorecard has liquid characteristics, for which the characteristic score is a smooth function of the characteristic over a liquid range. The smooth function is based on B-splines, typically cubic. In contrast, the characteristic scores for traditional scorecards are step functions of the characteristics. Previously, there were two ways to control the smoothness of the liquid characteristic score: (1) coarse classing where the fewer the number of classes, the smoother the curve; (2) the… 


Liquid Scorecards
This paper uses Quadratic Programming and B-Spline theory to find the Liquid Scorecard, that allows the component functions to be, at least partially, smooth curves.
A Practical Guide to Splines – Revised Edition
  • Springer, 2001.
  • 2001
A Quadratic Programming Approach to INFORM-NLP
  • Fair, Isaac restricted Technical Paper, July 14, 2000.
  • 2000
ObjectBoost – A Scoring Technology for Boosting a Specified Business Measure of a Score
  • Fair, Isaac Technical Paper, January 14, 2002.
  • 2002
Rules of Thumb for the INLP Penalty Parameter
  • Fair, Isaac Technical Paper, June 15, 2001.
  • 2001
An Analytic Approach to Coarse Classing
  • Fair, Isaac Technical Paper, April 10, 1998.
  • 1998
Boosting the Performance of Transaction Fraud Scores
  • Fair, Isaac Technical Paper, August 4, 1998.
  • 1998
RocBoost - A New technology for Boosting the ROC Curve at an Operating Point
  • Fair, Isaac Technical Paper, December 16, 1998.
  • 1998
Fair, Isaac restricted Technical Paper