Echo State Networks for Time Series Forecasting: Hyperparameter Sweep and Benchmarking

• URL: http://arxiv.org/abs/2602.03912v1
• Date: Tue, 03 Feb 2026 16:01:22 GMT
• Title: Echo State Networks for Time Series Forecasting: Hyperparameter Sweep and Benchmarking
• Authors: Alexander Häußer,
• Abstract summary: We evaluate whether a fully automatic, purely feedback-driven ESN can serve as a competitive alternative to widely used statistical forecasting methods.<n>Forecast accuracy is measured using MASE and sMAPE and benchmarked against simple benchmarks like drift and seasonal naive and statistical models.
• Score: 51.56484100374058
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: This paper investigates the forecasting performance of Echo State Networks (ESNs) for univariate time series forecasting using a subset of the M4 Forecasting Competition dataset. Focusing on monthly and quarterly time series with at most 20 years of historical data, we evaluate whether a fully automatic, purely feedback-driven ESN can serve as a competitive alternative to widely used statistical forecasting methods. The study adopts a rigorous two-stage evaluation approach: a Parameter dataset is used to conduct an extensive hyperparameter sweep covering leakage rate, spectral radius, reservoir size, and information criteria for regularization, resulting in over four million ESN model fits; a disjoint Forecast dataset is then used for out-of-sample accuracy assessment. Forecast accuracy is measured using MASE and sMAPE and benchmarked against simple benchmarks like drift and seasonal naive and statistical models like ARIMA, ETS, and TBATS. The hyperparameter analysis reveals consistent and interpretable patterns, with monthly series favoring moderately persistent reservoirs and quarterly series favoring more contractive dynamics. Across both frequencies, high leakage rates are preferred, while optimal spectral radii and reservoir sizes vary with temporal resolution. In the out-of-sample evaluation, the ESN performs on par with ARIMA and TBATS for monthly data and achieves the lowest mean MASE for quarterly data, while requiring lower computational cost than the more complex statistical models. Overall, the results demonstrate that ESNs offer a compelling balance between predictive accuracy, robustness, and computational efficiency, positioning them as a practical option for automated time series forecasting.

Related papers

• Low-Dimensional Adaptation of Rectified Flow: A New Perspective through the Lens of Diffusion and Stochastic Localization [59.04314685837778]
  Rectified flow (RF) has gained considerable popularity due to its generation efficiency and state-of-the-art performance.<n>In this paper, we investigate the degree to which RF automatically adapts to the intrinsic low dimensionality of the support of the target distribution to accelerate sampling.<n>We show that, using a carefully designed choice of the time-discretization scheme and with sufficiently accurate drift estimates, the RF sampler enjoys an complexity of order $O(k/varepsilon)$.
  arXiv  Detail & Related papers  (2026-01-21T22:09:27Z)
• Beyond Accuracy: A Stability-Aware Metric for Multi-Horizon Forecasting [0.0]
  We introduce the forecast accuracy and coherence score (forecast AC score for short) for measuring the quality of probabilistic multi-horizon forecasts.<n>Results demonstrate substantial improvements over traditional maximum likelihood estimation.
  arXiv  Detail & Related papers  (2026-01-15T21:26:57Z)
• Km-scale dynamical downscaling through conformalized latent diffusion models [45.94979929172337]
  Dynamical downscaling is crucial for deriving high-resolution meteorological fields from coarse-scale simulations.<n>Generative Diffusion models (DMs) have recently emerged as powerful data-driven tools for this task.<n>However, DMs lack finite-sample guarantees against overconfident predictions, resulting in miscalibrated grid-point-level uncertainty estimates.<n>We tackle this issue by augmenting the downscaling pipeline with a conformal prediction framework.
  arXiv  Detail & Related papers  (2025-10-15T08:41:36Z)
• Short-Term Regional Electricity Demand Forecasting in Argentina Using LSTM Networks [0.0]
  This study presents the development and optimization of a deep learning model to predict short-term hourly electricity demand in C'ordoba, Argentina.<n>The model achieved high predictive precision, with a mean absolute percentage error of 3.20% and a determination coefficient of 0.95.
  arXiv  Detail & Related papers  (2025-09-19T19:20:49Z)
• Hierarchical Evaluation Function: A Multi-Metric Approach for Optimizing Demand Forecasting Models [0.479839492673697]
  The Hierarchical Evaluation Function (HEF) is proposed as a multi-metric framework for hyperparameter optimization.<n>HEF integrates explanatory power (R2), sensitivity to extreme errors (RMSE), and average accuracy (MAE)<n>The performance of HEF was assessed using four widely recognized benchmark datasets in the forecasting domain.
  arXiv  Detail & Related papers  (2025-08-18T16:25:49Z)
• Empirical Comparison of Lightweight Forecasting Models for Seasonal and Non-Seasonal Time Series [1.9799527196428246]
  This study provides an empirical comparison between a Polynomial and a Radial Basis Network (RBFNN)<n>Model performance is evaluated by forecasting accuracy (using Mean Absolute Error, Root Mean Squared Error, and Coefficient Function of Variation of Root Mean Squared Error) and computational time.<n>Results show that the PC yields more accurate and faster forecasts for non seasonal series, whereas RBFNN performs better on seasonal patterns.
  arXiv  Detail & Related papers  (2025-05-02T10:12:23Z)
• Neural Networks with LSTM and GRU in Modeling Active Fires in the Amazon [0.0]
  This study presents a comprehensive methodology for modeling and forecasting the historical time series of active fire spots detected by the AQUA_M-T satellite in the Amazon, Brazil. The approach employs a mixed Recurrent Neural Network (RNN) model, combining Long Short-Term Memory (LSTM) and Gated Recurrent Unit (GRU) architectures to predict the monthly accumulations of daily detected active fire spots.
  arXiv  Detail & Related papers  (2024-09-04T13:11:59Z)
• Soft Random Sampling: A Theoretical and Empirical Analysis [59.719035355483875]
  Soft random sampling (SRS) is a simple yet effective approach for efficient deep neural networks when dealing with massive data. It selects a uniformly speed at random with replacement from each data set in each epoch. It is shown to be a powerful and competitive strategy with significant and competitive performance on real-world industrial scale.
  arXiv  Detail & Related papers  (2023-11-21T17:03:21Z)
• XRMDN: An Extended Recurrent Mixture Density Network for Short-Term Probabilistic Rider Demand Forecasting with High Volatility [16.047461063459846]
  We propose an Extended Recurrent Mixture Density Network (XRMDN) to process demand residuals and variance through correlated modules. XRMDN adeptly captures demand trends, thus significantly enhancing forecasting precision, particularly in high-volatility scenarios.
  arXiv  Detail & Related papers  (2023-10-15T14:18:42Z)
• Long-term drought prediction using deep neural networks based on geospatial weather data [75.38539438000072]
  High-quality drought forecasting up to a year in advance is critical for agriculture planning and insurance. We tackle drought data by introducing an end-to-end approach that adopts a systematic end-to-end approach. Key findings are the exceptional performance of a Transformer model, EarthFormer, in making accurate short-term (up to six months) forecasts.
  arXiv  Detail & Related papers  (2023-09-12T13:28:06Z)
• Forecast reconciliation for vaccine supply chain optimization [61.13962963550403]
  Vaccine supply chain optimization can benefit from hierarchical time series forecasting. Forecasts of different hierarchy levels become incoherent when higher levels do not match the sum of the lower levels forecasts. We tackle the vaccine sale forecasting problem by modeling sales data from GSK between 2010 and 2021 as a hierarchical time series.
  arXiv  Detail & Related papers  (2023-05-02T14:34:34Z)
• An Accurate and Fully-Automated Ensemble Model for Weekly Time Series Forecasting [9.617563440471928]
  We propose a forecasting method in this domain, leveraging state-of-the-art forecasting techniques. We consider different meta-learning architectures, algorithms, and base model pools. Our proposed method consistently outperforms a set of benchmarks and state-of-the-art weekly forecasting models.
  arXiv  Detail & Related papers  (2020-10-16T04:29:09Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.