mlsanityData to 14 Oct 2026

Deep State Space Recurrent Neural Networks for Time Series Forecasting

arXiv 2407.15236 ↗First posted 21 Jul 2024cs.LGcited by 6

Not on the map. Why?

Abstract (arXiv)

We explore various neural network architectures for modeling the dynamics of the cryptocurrency market. Traditional linear models often fall short in accurately capturing the unique and complex dynamics of this market. In contrast, Deep Neural Networks (DNNs) have demonstrated considerable proficiency in time series forecasting. This papers introduces novel neural network framework that blend the principles of econometric state space models with the dynamic capabilities of Recurrent Neural Networks (RNNs). We propose state space models using Long Short Term Memory (LSTM), Gated Residual Units (GRU) and Temporal Kolmogorov-Arnold Networks (TKANs). According to the results, TKANs, inspired by Kolmogorov-Arnold Networks (KANs) and LSTM, demonstrate promising outcomes.

Key facts. Cited by 6 papers in the map (data through 14 Oct 2026). Builds on 9 of its 31 references that are in the map. First posted on arXiv 21 Jul 2024.

Builds on

9 of 31 references.

References · 9

  1. 2014Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modelingcited by 2,367
  2. 2014On the Properties of Neural Machine Translation: Encoder-Decoder Approachescited by 1,304
  3. 2024KAN: Kolmogorov-Arnold Networkscited by 649
  4. 2015A Simple Way to Initialize Recurrent Networks of Rectified Linear Unitscited by 130
  5. 2024TKAN: Temporal Kolmogorov-Arnold Networkscited by 71
  6. 2024A Temporal Kolmogorov-Arnold Transformer for Time Series Forecastingcited by 52
  7. 2020Markovian RNN: An Adaptive Time Series Prediction Network with HMM-based Switching for Nonstationary Environmentscited by 9
  8. 2014The digital traces of bubbles: feedback cycles between socio-economic signals in the Bitcoin economycited by 4
  9. 2021Dimensionality reduction for prediction: Application to Bitcoin and Ethereumcited by 1

Built on by

Cited by year

Citing papers per year: 2024: 5; 2025: 1.

6 papers.

  1. 2024Adaptive Training of Grid-Dependent Physics-Informed Kolmogorov-Arnold Networkscited by 38
  2. 2024A Gated Residual Kolmogorov-Arnold Networks for Mixtures of Expertscited by 6
  3. 2024KAN we improve on HEP classification tasks? Kolmogorov-Arnold Networks applied to an LHC physics examplecited by 4
  4. 2024A Temporal Linear Network for Time Series Forecastingcited by 4
  5. 2024HiPPO-KAN: Efficient KAN Model for Time Series Analysiscited by 3
  6. 2025STAN: Smooth Transition Autoregressive Networkscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025CryptoMamba: Leveraging State Space Models for Accurate Bitcoin Price Prediction
  2. 2021Stochastic Recurrent Neural Network for Multistep Time Series Forecasting
  3. 2023Deep State-Space Model for Predicting Cryptocurrency Price
  4. 2026MoFE: A Novel Mixture-of-Experts Framework with Fourier Neural Operators for Cryptocurrency Forecasting
  5. 2021Deep Switching State Space Model (DS3M) for Nonlinear Time Series Forecasting with Regime Switching
  6. 2026Deep Learning for Financial Time Series: A Large-Scale Benchmark of Risk-Adjusted Performance
  7. 2024A Comprehensive Survey of Deep Learning for Time Series Forecasting: Architectural Diversity and Open Challenges
  8. 2023Effectively Modeling Time Series with Simple Discrete State Spaces