14th International Conference on Industrial Engineering and Operations Management

Automated Machine Learning Algorithms for Long-Term Time Series Forecasting

Ying Su & Morgan Wang
Publisher: IEOM Society International
0 Paper Citations
1 Views
1 Downloads
Abstract

Long-term time series forecasting is an important research area for automated machine learning (AutoML). Currently forecasting based on either machine learning or traditional statistical model is usually built by experts and it requires significant manual effort: from model construction, feature engineering, and hyper-parameter tuning to construction of the time series model. Automation is not possible since there are too many human interventions. To overcome these limitations, this article proposed to use a Recurrent Neural Network (RNN) variant, Long Short-Term Memory (LSTM), through the memory cell and gates to perform long-term time series prediction. We have shown that this proposed approach is better than traditional Autoregressive Integrated Moving Average (ARIMA). In addition, we also found it is better than other neural network systems.

Published in: 14th International Conference on Industrial Engineering and Operations Management, Dubai, UAE

Publisher: IEOM Society International
Date of Conference: February 12-14, 2024

ISBN: 979-8-3507-1734-1
ISSN/E-ISSN: 2169-8767