# Self-Adaptive Scale Handling for Forecasting Time Series with Scale Heterogeneity

Source: [Self-Adaptive Scale Handling for Forecasting Time Series with Scale Heterogeneity](<https://www.sota2.com/research/paper/6a34cd45206542251d7c6116>)

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

Data updated: 2026-06-20T05:00:05.764Z

Authors: Xu Zhang, Zhengang Huang, Yunzhi Wu, Xun Lu, Erpeng Qi, Yunkai Chen, Zhongya Xue, Peng Wang, Wei Wang

Published: 2026-06-18T09:44:25.000Z

## Abstract

Current time series forecasting (TSF) research predominantly focuses on scale-homogeneous data, where different time series share similar numerical magnitude ranges. However, in real-world industrial scenarios such as financial product sales, different time series often differ by orders of magnitude (scale heterogeneity). Since these series share similar temporal patterns, joint modeling is desirable for better data utilization, yet existing scaling methods either compress low-scale signals (global normalization) or destroy semantic discriminability and amplify inverse-scaling errors (window-based scaling). This paper proposes a self-Adaptive Scale-handling (AS) module that learns adaptive scale factors tailored to each input, preserving semantic discriminability while reducing inverse-scaling errors. AS consists of Scale Calibrating (SC), which calibrates prior mean scaling factors through neural networks, and Scaling Selection (SS), which decides whether to apply calibration or retain the original factor, avoiding over-calibration. Experiments on real-world fund sales datasets from Ant Fortune and Alipay show that AS seamlessly integrates into popular TSF models and consistently improves their performance. The code and dataset are available at the link https://github.com/Meteor-Stars/ASTSF.

## 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 Fund1 horizon 10](<https://www.sota2.com/research/sota/time-series-forecasting-on-fund1-horizon-10.md>): Time Series Forecasting; Fund1 horizon 10; WMA: 93.15.

- [Time Series Forecasting on Fund2 horizon 10](<https://www.sota2.com/research/sota/time-series-forecasting-on-fund2-horizon-10.md>): Time Series Forecasting; Fund2 horizon 10; WMA: 83.73.

- [Time Series Forecasting on Fund1 horizon 5](<https://www.sota2.com/research/sota/time-series-forecasting-on-fund1-horizon-5.md>): Time Series Forecasting; Fund1 horizon 5; WMA: 83.07.

- [Time Series Forecasting on Fund2 (horizon 5)](<https://www.sota2.com/research/sota/time-series-forecasting-on-fund2-horizon-5.md>): Time Series Forecasting; Fund2 (horizon 5); WMA: 75.56.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2606.20010>)

[PDF](<https://arxiv.org/pdf/2606.20010.pdf>)
