Neural forecasting at scale

09/20/2021
by   Philippe Chatigny, et al.
0

We study the problem of efficiently scaling ensemble-based deep neural networks for time series (TS) forecasting on a large set of time series. Current state-of-the-art deep ensemble models have high memory and computational requirements, hampering their use to forecast millions of TS in practical scenarios. We propose N-BEATS(P), a global multivariate variant of the N-BEATS model designed to allow simultaneous training of multiple univariate TS forecasting models. Our model addresses the practical limitations of related models, reducing the training time by half and memory requirement by a factor of 5, while keeping the same level of accuracy. We have performed multiple experiments detailing the various ways to train our model and have obtained results that demonstrate its capacity to support zero-shot TS forecasting, i.e., to train a neural network on a source TS dataset and deploy it on a different target TS dataset without retraining, which provides an efficient and reliable solution to forecast at scale even in difficult forecasting conditions.

READ FULL TEXT

page 14

page 27

03/26/2020

Zero-shot and few-shot time series forecasting with ordinal regression recurrent neural networks

Recurrent neural networks (RNNs) are state-of-the-art in several sequent...
07/16/2022

Generalizable Memory-driven Transformer for Multivariate Long Sequence Time-series Forecasting

Multivariate long sequence time-series forecasting (M-LSTF) is a practic...
03/02/2022

Boosted Ensemble Learning based on Randomized NNs for Time Series Forecasting

Time series forecasting is a challenging problem particularly when a tim...
12/30/2020

Ensembles of Localised Models for Time Series Forecasting

With large quantities of data typically available nowadays, forecasting ...
03/27/2020

Financial Time Series Representation Learning

This paper addresses the difficulty of forecasting multiple financial ti...
05/03/2020

If You Like It, GAN It. Probabilistic Multivariate Times Series Forecast With GAN

The contribution of this paper is two-fold. First, we present ProbCast -...
11/01/2018

Taylor-based Optimized Recursive Extended Exponential Smoothed Neural Networks Forecasting Method

A newly introduced method called Taylor-based Optimized Recursive Extend...