DBLoss: Decomposition-based Loss Function for Time Series Forecasting

TL;DR

DBLoss is a novel loss function for time series forecasting that decomposes series into trend and seasonality components, improving model accuracy across various datasets.

Contribution

The paper introduces DBLoss, a decomposition-based loss function that enhances forecasting accuracy by separately modeling trend and seasonality within the loss calculation.

Findings

DBLoss improves forecasting accuracy on multiple real-world datasets.

It can be integrated with any deep learning forecasting model.

Experimental results show significant performance gains.

Abstract

Time series forecasting holds significant value in various domains such as economics, traffic, energy, and AIOps, as accurate predictions facilitate informed decision-making. However, the existing Mean Squared Error (MSE) loss function sometimes fails to accurately capture the seasonality or trend within the forecasting horizon, even when decomposition modules are used in the forward propagation to model the trend and seasonality separately. To address these challenges, we propose a simple yet effective Decomposition-Based Loss function called DBLoss. This method uses exponential moving averages to decompose the time series into seasonal and trend components within the forecasting horizon, and then calculates the loss for each of these components separately, followed by weighting them. As a general loss function, DBLoss can be combined with any deep learning forecasting model. Extensive experiments demonstrate that DBLoss significantly improves the performance of state-of-the-art models across diverse real-world datasets and provides a new perspective on the design of time series loss functions.