DeepAR: Probabilistic Forecasting with Autoregressive Recurrent Networks
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 e.g. for reducing excess inventory in supply chains. In this talk, I will present some of the forecasting challenges at Amazon and then introduce 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-word forecasting data sets that our methodology is more accurate than competing state-of-the-art models, without requiring any manual feature engineering.
Jan Gasthaus is a machine learning scientist in Amazon’s Core Machine Learning team, working mainly on time series forecasting and large-scale probabilistic machine learning. He is passionate about developing novel machine learning solutions for addressing challenging business problems with scalable machine learning systems, all the way from scientific ideation to productization. Prior to joining Amazon, Jan obtained a BS in Cognitive Science from the University of Osnabrueck, a MS in Intelligent Systems from UCL, and pursued a PhD at the Gatsby Unit, UCL, focusing on Nonparametric Bayesian methods for sequence data.