Shipping market time series forecasting via an Ensemble Deep Dual-Projection Echo State Network

Xuefei Song, Zhong Shuo Chen*

*Corresponding author for this work

Research output: Contribution to journalArticlepeer-review


The Echo State Network (ESN) is a specific type of recurrent neural network characterized by random initialization of recurrent and input connections. The reservoir structure effectively reduces computational workload. However, the redundancy in the reservoir network can degrade predictive accuracy, especially in time series forecasting tasks. The challenge of extracting dependable and meaningful features from high-dimensional reservoirs remains an open question. Additionally, the presence of high-dimensional reservoirs in small datasets can lead to ill-conditioned problems. Therefore, the objectives of this study are twofold: to reduce reservoir dimensionality and extract meaningful features concurrently. We first employ a dual-projection module to fine-tune the reservoir and build an ensemble deep architecture to achieve this. Empirical experimentation confirms the superior predictive performance of our proposed approach when applied to shipping market datasets, outperforming several baseline models and traditional benchmarks.

Original languageEnglish
Article number109218
JournalComputers and Electrical Engineering
Publication statusPublished - Jul 2024


  • Deep learning
  • Echo state network (ESN)
  • Ensemble neural networks
  • Forecasting
  • Randomized neural network


Dive into the research topics of 'Shipping market time series forecasting via an Ensemble Deep Dual-Projection Echo State Network'. Together they form a unique fingerprint.

Cite this