Markovian RNN: An Adaptive Time Series Prediction Network With HMM-Based Switching for Nonstationary Environments

Creative Commons License

Ilhan F., Karaahmetoglu O., Balaban I., Kozat S. S.

IEEE Transactions on Neural Networks and Learning Systems, vol.34, no.2, pp.715-728, 2023 (SCI-Expanded) identifier identifier identifier

  • Publication Type: Article / Article
  • Volume: 34 Issue: 2
  • Publication Date: 2023
  • Doi Number: 10.1109/tnnls.2021.3100528
  • Journal Name: IEEE Transactions on Neural Networks and Learning Systems
  • Journal Indexes: Science Citation Index Expanded (SCI-EXPANDED), Scopus, Academic Search Premier, PASCAL, Aerospace Database, Applied Science & Technology Source, Biotechnology Research Abstracts, Business Source Elite, Business Source Premier, Communication Abstracts, Compendex, Computer & Applied Sciences, EMBASE, INSPEC, MEDLINE, Metadex, Civil Engineering Abstracts
  • Page Numbers: pp.715-728
  • Keywords: Hidden Markov models, Time series analysis, Switches, Predictive models, Task analysis, Adaptation models, Data models, Hidden Markov models (HMMs), nonlinear regression, nonstationarity, recurrent neural networks (RNNs), regime switching, time series prediction, NEURAL-NETWORKS, MIXTURE, MODEL
  • Middle East Technical University Affiliated: Yes

Abstract

We investigate nonlinear regression for nonstationary sequential data. In most real-life applications such as business domains including finance, retail, energy, and economy, time series data exhibit nonstationarity due to the temporally varying dynamics of the underlying system. We introduce a novel recurrent neural network (RNN) architecture, which adaptively switches between internal regimes in a Markovian way to model the nonstationary nature of the given data. Our model, Markovian RNN employs a hidden Markov model (HMM) for regime transitions, where each regime controls hidden state transitions of the recurrent cell independently. We jointly optimize the whole network in an end-to-end fashion. We demonstrate the significant performance gains compared to conventional methods such as Markov Switching ARIMA, RNN variants and recent statistical and deep learning-based methods through an extensive set of experiments with synthetic and real-life datasets. We also interpret the inferred parameters and regime belief values to analyze the underlying dynamics of the given sequences.