QCNN: Quantile Convolutional Neural Network

08/21/2019

∙

by   Gábor Petneházi, et al.

∙

0

∙

share

A dilated causal one-dimensional convolutional neural network architecture is proposed for quantile regression. The model can forecast any arbitrary quantile, and it can be trained jointly on multiple similar time series. An application to Value at Risk forecasting shows that QCNN outperforms linear quantile regression and constant quantile estimates.