DeepAR: Probabilistic Forecasting with Autoregressive Recurrent Networks
David Salinas, Valentin Flunkert, Jan Gasthaus Amazon Research Germany
Abstract
Probabilistic forecasting, i.e. estimating the probability distribution of a time series’ future given its past, is a key enabler for optimizing business processes. In retail businesses, for example, forecasting demand is crucial for having the right inventory available at the right time at the right place. In this paper we propose DeepAR, a methodology for producing accurate probabilistic forecasts, based on training an auto-regressive recurrent network model on a large number of related time series. We demonstrate how by applying deep learning techniques to forecasting, one can overcome many of the challenges faced by widely-used classical approaches to the problem. We show through extensive empirical evaluation on several real-world forecasting data sets accuracy improvements of around 15% compared to state-of-the-art methods.
中文速览
用循环神经网络同时学习海量相关时间序列的规律，从而对每一条时间序列给出准确的概率预测——这正是 DeepAR 要解决的核心问题。面对零售、能源等场景中动辄数百万条、量级差异极大的时间序列，传统方法（如 ARIMA、指数平滑）只能对单条序列分别建模，费时费力且难以泛化；DeepAR 则用一个基于 LSTM 的自回归循环网络在所有序列上联合训练，以负二项分布（negative binomial likelihood）处理计数数据的过离散问题，并通过规模归一化应对量级悬殊的挑战。在多个真实数据集上的实验表明，DeepAR 比当时最先进的方法平均提升约 15% 的预测精度，且能以蒙特卡洛采样的形式输出完整的预测分布，还能为历史数据极少的新品直接给出预测。这项工作的意义在于，它证明了深度学习可以真正解决大规模概率预测问题，让下游业务（如库存优化）能够在不确定性下做出更优决策。
原文 arXiv:1704.04110;中英对照 + 大白话阅读 https://aha.fim.ai/paper/1704.04110v3