Addressing Prediction Delays in Time Series Forecasting: A Continuous GRU Approach with Derivative Regularization

TL;DR

This paper introduces a continuous-time GRU model with derivative regularization to reduce prediction delay in time series forecasting, outperforming traditional methods on multiple metrics.

Contribution

It proposes a novel continuous-time GRU architecture with explicit derivative supervision to mitigate prediction delay in time series forecasting.

Findings

Outperforms traditional models in MSE, DTW, and TDI metrics.

Demonstrates significantly lower prediction delay across various datasets.

Effective in applications like finance and weather forecasting.

Abstract

Time series forecasting has been an essential field in many different application areas, including economic analysis, meteorology, and so forth. The majority of time series forecasting models are trained using the mean squared error (MSE). However, this training based on MSE causes a limitation known as prediction delay. The prediction delay, which implies the ground-truth precedes the prediction, can cause serious problems in a variety of fields, e.g., finance and weather forecasting -- as a matter of fact, predictions succeeding ground-truth observations are not practically meaningful although their MSEs can be low. This paper proposes a new perspective on traditional time series forecasting tasks and introduces a new solution to mitigate the prediction delay. We introduce a continuous-time gated recurrent unit (GRU) based on the neural ordinary differential equation (NODE) which can supervise explicit time-derivatives. We generalize the GRU architecture in a continuous-time manner and minimize the prediction delay through our time-derivative regularization. Our method outperforms in metrics such as MSE, Dynamic Time Warping (DTW) and Time Distortion Index (TDI). In addition, we demonstrate the low prediction delay of our method in a variety of datasets.