DeepAR: Probabilistic Forecasting with Autoregressive Recurrent Networks (2017-04-13T00:00:00.000000Z)

TL;DR

DeepAR is proposed, a methodology for producing accurate probabilistic forecasts, based on training an auto regressive recurrent network model on a large number of related time series, with accuracy improvements of around 15% compared to state-of-the-art methods.

Authors

Valentin Flunkert

2 papers

Jan Gasthaus

2 papers

David Salinas

2 papers

TL;DR

Authors

References48 items

Forecasting Big Time Series: Theory and Practice

N-BEATS: Neural basis expansion analysis for interpretable time series forecasting

Deep Learning-Based Multivariate Probabilistic Forecasting for Short-Term Scheduling in Power Markets

The M4 Competition: Results, findings, conclusion and way forward

Forecasting Across Time Series Databases using Long Short-Term Memory Networks on Groups of Similar Series

Bayesian Intermittent Demand Forecasting for Large Inventories

Temporal Regularized Matrix Factorization for High-dimensional Time Series Prediction

Phased LSTM: Accelerating Recurrent Network Training for Long or Event-based Sequences

WaveNet: A Generative Model for Raw Audio

MXNet: A Flexible and Efficient Machine Learning Library for Heterogeneous Distributed Systems

Scheduled Sampling for Sequence Prediction with Recurrent Neural Networks

DRAW: A Recurrent Neural Network For Image Generation

Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift

On the identification of sales forecasting models in the presence of promotions

Adam: A Method for Stochastic Optimization

Sequence to Sequence Learning with Neural Networks

Effective Bayesian Modeling of Groups of Related Count Time Series

Forecasting: principles and practice

Generating Sequences With Recurrent Neural Networks

Measuring forecasting accuracy : the case of judgmental adjustments to SKU-level demand forecasts

Intermittent demand forecasts with neural networks

Forecasting the intermittent demand for slow-moving inventories: A modelling approach

Optimal combination forecasts for hierarchical time series

A hybrid ARIMA and artificial neural networks model to forecast particulate matter in urban areas: The case of Temuco, Chile

Automatic Time Series Forecasting: The forecast Package for R

Empirical evidence on individual, group and shrinkage seasonal indices

Forecasting and operational research: a review

Designing and managing the supply chain : concepts, strategies, and case studies

A dynamic artificial neural network model for forecasting time series events

The State of the Art

Lumpy demand forecasting using neural networks

Applying LSTM to Time Series Predictable through Time-Window Approaches

Designing and Managing the Supply Chain Concepts, Strategies, and Case Studies

FORECASTING WITH ARTIFICIAL NEURAL NETWORKS: THE STATE OF THE ART

Long Short-Term Memory

Designing a neural network for forecasting financial and economic time series

Time Series Analysis: Forecasting and Control

Forecasting and Stock Control for Intermittent Demands

Some Recent Advances in Forecasting and Control

An Analysis of Transformations

Deep State Space Models for Time Series Forecasting

GENERATIVE ADVERSARIAL NETS

DeepAR: Probabilistic Forecasting

Ensembles for Time Series Forecasting

The Application of Product-Group Seasonal Indexes to Individual Products

Forecasting with Exponential Smoothing

Chapter 4 Forecast Combinations

Adaptive computation and machine learning

Field of Study

Journal Information

Name

Volume

Venue Information

Name

Type

URL

Alternate Names