NeuralForecast is a highly modular framework capable of augmenting a wide variety of robust neural network architectures with different point or probability outputs as defined by their optimization objectives.

Point losses

Scale-DependentPercentage-ErrorsScale-IndependentRobust
MAEMAPEMASEHuber
MSEsMAPETukey
RMSEHuberMQLoss

Probabilistic losses

Parametric ProbabilitiesNon-Parametric Probabilities
NormalQuantileLoss
StudenTMQLoss
PoissonHuberQLoss
Negative BinomialHuberMQLoss
TweedieIQLoss
PMM /GMM / NBMMISQF