Markovian RNN: An Adaptive Time Series Prediction Network with HMM-based Switching for Nonstationary Environments
This addresses the challenge of modeling nonstationary sequential data in domains like finance and retail, though it is an incremental improvement over existing methods.
The paper tackles the problem of predicting nonstationary time series data by introducing a Markovian RNN that adaptively switches between internal regimes using a hidden Markov model. It demonstrates significant performance gains over vanilla RNN and Markov Switching ARIMA in experiments with synthetic and real-life datasets.
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.