Online Data Augmentation for Forecasting with Deep Learning

TL;DR

This paper proposes an online data augmentation framework for deep learning-based time series forecasting, generating synthetic data during training to improve model performance without large offline datasets.

Contribution

It introduces a novel online augmentation method that creates synthetic samples during training, maintaining data balance and enhancing forecasting accuracy.

Findings

Online augmentation improves forecasting accuracy.

Framework works across multiple datasets and models.

Eliminates need for storing large augmented datasets.

Abstract

Deep learning approaches are increasingly used to tackle forecasting tasks involving datasets with multiple univariate time series. A key factor in the successful application of these methods is a large enough training sample size, which is not always available. Synthetic data generation techniques can be applied in these scenarios to augment the dataset. Data augmentation is typically applied offline before training a model. However, when training with mini-batches, some batches may contain a disproportionate number of synthetic samples that do not align well with the original data characteristics. This work introduces an online data augmentation framework that generates synthetic samples during the training of neural networks. By creating synthetic samples for each batch alongside their original counterparts, we maintain a balanced representation between real and synthetic data throughout the training process. This approach fits naturally with the iterative nature of neural network training and eliminates the need to store large augmented datasets. We validated the proposed framework using 3797 time series from 6 benchmark datasets, three neural architectures, and seven synthetic data generation techniques. The experiments suggest that online data augmentation leads to better forecasting performance compared to offline data augmentation or no augmentation approaches. The framework and experiments are publicly available.