# Dynamic Multi-period Experts for Online Time Series Forecasting

Source: [Dynamic Multi-period Experts for Online Time Series Forecasting](<https://www.sota2.com/research/paper/69b0f6f72d603e6de3e45c82>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-03-12T05:00:04.726Z

Authors: Seungha Hong, Sukang Chae, Suyeon Kim, Sanghwan Jang, Hwanjo Yu

Published: 2026-03-10T01:09:30.000Z

## Abstract

Online Time Series Forecasting (OTSF) requires models to continuously adapt to concept drift. However, existing methods often treat concept drift as a monolithic phenomenon. To address this limitation, we first redefine concept drift by categorizing it into two distinct types: Recurring Drift, where previously seen patterns reappear, and Emergent Drift, where entirely new patterns emerge. We then propose DynaME (Dynamic Multi-period Experts), a novel hybrid framework designed to effectively address this dual nature of drift. For Recurring Drift, DynaME employs a committee of specialized experts that are dynamically fitted to the most relevant historical periodic patterns at each time step. For Emergent Drift, the framework detects high-uncertainty scenarios and shifts reliance to a stable, general expert. Extensive experiments on several benchmark datasets and backbones demonstrate that DynaME effectively adapts to both concept drifts and significantly outperforms existing baselines.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

- [Time Series Forecasting on ETTh2 (MSE H=24, 48, 96)](<https://www.sota2.com/research/sota/time-series-forecasting-on-etth2-mse-h-24-48-96.md>): Time Series Forecasting; ETTh2; MSE (H=24): 1.676.

- [Time Series Forecasting on ETTm1 (MSE H=24, H=48, H=96)](<https://www.sota2.com/research/sota/time-series-forecasting-on-ettm1-mse-h-24-h-48-h-96.md>): Time Series Forecasting; ETTm1; MSE (H=24): 0.439.

- [Time Series Forecasting on Traffic (MSE at H=24, H=48, H=96)](<https://www.sota2.com/research/sota/time-series-forecasting-on-traffic-mse-at-h-24-h-48-h-96.md>): Time Series Forecasting; Traffic; MSE (H=24): 0.376.

- [Time Series Forecasting on ECL (H=24, 48, 96 MSE)](<https://www.sota2.com/research/sota/time-series-forecasting-on-ecl-h-24-48-96-mse.md>): Time Series Forecasting; ECL; MSE (Horizon 24): 3.834.

- [Time Series Forecasting on Weather (MSE H=24, H=48, H=96)](<https://www.sota2.com/research/sota/time-series-forecasting-on-weather-mse-h-24-h-48-h-96.md>): Time Series Forecasting; Weather; MSE (H=24): 0.828.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2603.09062>)

[PDF](<https://arxiv.org/pdf/2603.09062.pdf>)
