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

TL;DR

This paper introduces a novel RNN architecture that adaptively switches between regimes using an HMM to effectively model nonstationary time series data, demonstrating superior performance over traditional methods.

Contribution

The paper proposes the Markovian RNN, integrating HMM-based regime switching into RNNs for better modeling of nonstationary sequences, optimized end-to-end.

Findings

Significant performance improvements over vanilla RNN and ARIMA.

Effective modeling of nonstationary data with regime switching.

Interpretability of regime dynamics through inferred parameters.

Abstract

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.