A Multi-Horizon Quantile Recurrent Forecaster · HackerPapers discussions

A Multi-Horizon Quantile Recurrent Forecaster — mentioned by jwilber

Tue, 13 Dec 2022 02:16:23 GMT

I appreciate the response but I admit I'm a bit confused - maybe it's the case that you're not familiar with the need for modern forecasting? Some of your 'defense' is just flat out wrong. A few points: - You write: 1. "Clean data would benefit most models, not just non-deep learning models. Missing data introduces bias even in DL models." and 2. "Because a cold start is not a time series data set. Why would time series methods work on non time series data." Clean data is good, yes, thanks for the insight. But 1. missing data is a huge issue for model quality, particularly for…

Paper and discussion history. A mention is not an endorsement.

A Multi-Horizon Quantile Recurrent Forecaster — mentioned by lr1970

Thu, 01 Jul 2021 13:07:27 GMT

> Do you have any favourite libraries for producing such? For modern Deep Learning based probabilistic forecasting you can try DeepAR with parametric likelihood function [0] or Multi-Horizon Quantile RNN (non-parametric) [1]. The implementations of these models in Pytorch and MXnet are scattered all over the place. [0] https://arxiv.org/abs/1704.04110 [1] https://arxiv.org/abs/1711.11053 EDIT: formatting

Paper and discussion history. A mention is not an endorsement.

A Multi-Horizon Quantile Recurrent Forecaster — mentioned by solidasparagus

Wed, 13 Nov 2019 23:41:11 GMT

I completely disagree with the assumption that because something has been done for 60+ years it won't be improved by new, extremely relevant technologies. Amazon is very effective at both OR and organizational dynamics, but they found massive savings by using ML to predict demand and thus inventory/costs (Research is here - https://arxiv.org/pdf/1711.11053.pdf).

Paper and discussion history. A mention is not an endorsement.