# Markovian RNN: An Adaptive Time Series Prediction Network with HMM-based Switching for Nonstationary Environments

arXiv: https://arxiv.org/abs/2006.10119 · HTML: https://mlsanity.com/paper/2006.10119/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 17 Jun 2020.

## Built on by (most cited first, 9 of 9)

- [Distributional Drift Adaptation with Temporal Conditional Variational Autoencoder for Multivariate Time Series Forecasting](https://mlsanity.com/paper/2209.00654/) (2022)
- [Deep State Space Recurrent Neural Networks for Time Series Forecasting](https://mlsanity.com/paper/2407.15236/) (2024)
- [TS-LIF: A Temporal Segment Spiking Neuron Network for Time Series Forecasting](https://mlsanity.com/paper/2503.05108/) (2025)
- [Delayed Memory Unit: Modelling Temporal Dependency Through Delay Gate](https://mlsanity.com/paper/2310.14982/) (2023)
- [The Sigma-max System Induced from Randomness & Fuzziness and its Application in Time Series Prediction](https://mlsanity.com/paper/2110.07722/) (2021)
- [A Policy Gradient-Based Sequence-to-Sequence Method for Time Series Prediction](https://mlsanity.com/paper/2406.09643/) (2024)
- [Adaptive Fuzzy Time Series Forecasting via Partially Asymmetric Convolution and Sub-Sliding Window Fusion](https://mlsanity.com/paper/2507.20641/) (2025)
- [Liquid Neural Network Models for Natural Gas Spot Price Time-Series Forecasting](https://mlsanity.com/paper/2604.24788/) (2026)
- [DRL-STAF: A Deep Reinforcement Learning Framework for State-Aware Forecasting of Complex Multivariate Hidden Markov Processes](https://mlsanity.com/paper/2605.14632/) (2026)

## Abstract (arXiv)

We investigate nonlinear regression for nonstationary sequential data. In most real-life applications such as business domains including finance, retail, energy and economy, timeseries data exhibits 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 vanilla RNN and conventional methods such as Markov Switching ARIMA 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.