arxivst stuff from arxiv that you should probably bookmark

DeepAR: Probabilistic Forecasting with Autoregressive Recurrent Networks

Abstract · Apr 13, 2017 13:11 ·

forecasting supply series time forecasts deepar forecast probabilistic cs-ai cs-lg stat-ml

Arxiv Abstract

  • Valentin Flunkert
  • David Salinas
  • Jan Gasthaus

A key enabler for optimizing business processes is accurately estimating the probability distribution of a time series future given its past. Such probabilistic forecasts are crucial for example for reducing excess inventory in supply chains. In this paper we propose DeepAR, a novel methodology for producing accurate probabilistic forecasts, based on training an auto-regressive recurrent network model on a large number of related time series. We show through extensive empirical evaluation on several real-world forecasting data sets that our methodology is more accurate than state-of-the-art models, while requiring minimal feature engineering.

Read the paper (pdf) »