TY - JOUR

T1 - Financial prediction with constrained tail risk

AU - Trindade, A. Alexandre

AU - Uryasev, Stan

AU - Shapiro, Alexander

AU - Zrazhevsky, Grigory

PY - 2007/11

Y1 - 2007/11

N2 - A new class of asymmetric loss functions derived from the least absolute deviations or least squares loss with a constraint on the mean of one tail of the residual error distribution, is introduced for analyzing financial data. Motivated by risk management principles, the primary intent is to provide "cautious" forecasts under uncertainty. The net effect on fitted models is to shape the residuals so that on average only a prespecified proportion of predictions tend to fall above or below a desired threshold. The loss functions are reformulated as objective functions in the context of parameter estimation for linear regression models, and it is demonstrated how optimization can be implemented via linear programming. The method is a competitor of quantile regression, but is more flexible and broader in scope. An application is illustrated on prediction of NDX and SPX index returns data, while controlling the magnitude of a fraction of worst losses.

AB - A new class of asymmetric loss functions derived from the least absolute deviations or least squares loss with a constraint on the mean of one tail of the residual error distribution, is introduced for analyzing financial data. Motivated by risk management principles, the primary intent is to provide "cautious" forecasts under uncertainty. The net effect on fitted models is to shape the residuals so that on average only a prespecified proportion of predictions tend to fall above or below a desired threshold. The loss functions are reformulated as objective functions in the context of parameter estimation for linear regression models, and it is demonstrated how optimization can be implemented via linear programming. The method is a competitor of quantile regression, but is more flexible and broader in scope. An application is illustrated on prediction of NDX and SPX index returns data, while controlling the magnitude of a fraction of worst losses.

KW - Asymmetric loss

KW - Constrained regression

KW - Quantile regression

KW - Risk measure

KW - Value-at-risk

UR - http://www.scopus.com/inward/record.url?scp=35448973220&partnerID=8YFLogxK

U2 - 10.1016/j.jbankfin.2007.04.014

DO - 10.1016/j.jbankfin.2007.04.014

M3 - Article

AN - SCOPUS:35448973220

VL - 31

SP - 3524

EP - 3538

JO - Journal of Banking and Finance

JF - Journal of Banking and Finance

SN - 0378-4266

IS - 11

ER -