Combining Forecasts of Time Series with Complex Seasonality Using LSTM-Based Meta-Learning

Engineering Proceedings

article

Grzegorz Dudek¹ 

[1] Electrical Engineering Faculty, Czestochowa University of Technology

关键词: ensemble forecasting;    LSTM;    machine learning;    multiple seasonal patterns;    short-term load forecasting;   

DOI  :  10.3390/engproc2023039053

来源: mdpi

【 摘 要 】

In this paper, we propose a method for combining forecasts generated by different models based on long short-term memory (LSTM) ensemble learning. While typical approaches for combining forecasts involve simple averaging or linear combinations of individual forecasts, machine learning techniques enable more sophisticated methods of combining forecasts through meta-learning, leading to improved forecasting accuracy. LSTM’s recurrent architecture and internal states offer enhanced possibilities for combining forecasts by incorporating additional information from the recent past. We define various meta-learning variants for seasonal time series and evaluate the LSTM meta-learner on multiple forecasting problems, demonstrating its superior performance compared to simple averaging and linear regression.

【 授权许可】

Unknown