Could you give me some examples and/or references on "risk-averse" loss functions (i.e. penalizing the underestimates more then the overestimates)?
$\begingroup$
$\endgroup$
-
1$\begingroup$ Do you mean like the loss function addressed at stats.stackexchange.com/questions/251600? $\endgroup$ – whuber♦ Mar 18 '17 at 19:11
$\begingroup$
$\endgroup$
Bayesian Methods for Hackers has a pretty informative chapter on loss functions and touches on this. They provide python function below as an example of a loss function that penalizes overestimates more heavily:
def stock_loss(true_return, yhat, alpha = 100.):
if true_return * yhat < 0:
#opposite signs, not good
return alpha*yhat**2 - np.sign(true_return)*yhat \
+ abs(true_return)
else:
return abs(true_return - yhat)
Note: you don't need to go full bayesian for this chapter to be relevant
