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

Fatih Ilhan, Oguzhan Karaahmetoglu, Ismail Balaban, Suleyman Serdar Kozat
2020 arXiv   pre-print
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
more » ... s 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.
arXiv:2006.10119v1 fatcat:4calty7qrffnvpftwzlpe36bj4