İlhan, FatihKaraahmetoğlu, OğuzhanBalaban, İ.Kozat, Süleyman Serdar2024-03-192024-03-192023-02-012162-237Xhttps://hdl.handle.net/11693/114924We 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.englishHidden Markov models (HMMs)Nonlinear regressionNonstationarityRecurrent neural networks (RNNs)Regime switchingTime series predictionArticle10.1109/TNNLS.2021.31005282162-2388