Proving Prediction Prudence

@article{Tasche2020ProvingPP,
  title={Proving Prediction Prudence},
  author={Dirk Tasche},
  journal={Risk Management eJournal},
  year={2020}
}
  • D. Tasche
  • Published 2020
  • Economics, Mathematics
  • Risk Management eJournal
We study how to perform tests on samples of pairs of observations and predictions in order to assess whether or not the predictions are prudent. Prudence requires that that the mean of the difference of the observation-prediction pairs can be shown to be significantly negative. For safe conclusions, we suggest testing both unweighted (or equally weighted) and weighted means and explicitly taking into account the randomness of individual pairs. The test methods presented are mainly specified as… Expand

References

SHOWING 1-10 OF 24 REFERENCES
A proposed framework for backtesting loss given default models
The Basel Accords require financial institutions to regularly validate their loss given default (LGD) models. This is crucial so banks are not misestimating the minimum required capital to protectExpand
Out-of-Time Validation of Default Probabilities within the Basel Accord: A Comparative Study
The probability of a default determines capital requirements set by the Basel Accord. To back-test default probabilities is therefore possibly the single most important task when validating creditExpand
Exposure at Default Modeling - A Theoretical and Empirical Assessment of Estimation Approaches and Parameter Choice
TLDR
This empirical analysis is based on a large and unique dataset from a retail portfolio of a European bank and empirically demonstrates that using the credit conversion factor is preferable to the loan equivalent factor, Exposure at default factor, and direct exposure at default estimation to achieve high estimation accuracy. Expand
The Law of Total Odds
The law of total probability may be deployed in binary classication exercises to estimate the unconditional class probabilities if the class proportions in the training set are not representative ofExpand
The Art of Probability-of-Default Curve Calibration
PD curve calibration refers to the transformation of a set of rating grade level probabilities of default (PDs) to another average PD level that is determined by a change of the underlyingExpand
Objective Bayesian estimation of the probability of default
type="main" xml:id="rssc12107-abs-0001"> Reliable estimation of the probability of default (PD) of a customer is one of the most important tasks in credit risk modelling for banks applying theExpand
Introduction to Probability and Statistics.
TLDR
The authors explain how to meaningfully describe real sets of data, what the statistical tests mean in terms of their practical applications, how to evaluate the validity of the assumptions behind statistical tests, and what to do when statistical assumptions have been violated. Expand
Probability and Statistics
Entropy and Martingale (K B Athreya & M G Nadkarni) Marginal Quantiles: Asymptotics for Functions of Order Statistics (J Babu) Statistics on Manifolds with Applications to Shape Spaces (RExpand
Probability and Statistics
IF k1(x) is any non-negative function in L1 (− ∞, + ∞), let us write: for n = 2, 3, … Then the function: is defined almost everywhere (although it is possibly infinite for some, or all, x).
  • Instructions for reporting the validation results of internal models: IRB Pillar I models for credit risk. European Central Bank -Banking Supervision
  • 2019
...
1
2
3
...