Neural Decomposition of Time-Series Data for Effective Generalization
This addresses forecasting problems in fields like economics and environmental science, but it is incremental as it builds on existing decomposition and neural network approaches.
The paper tackles time-series forecasting by introducing Neural Decomposition (ND), a neural network method that decomposes data into periodic and nonperiodic components, and reports that ND outperforms several existing techniques like LSTM and ARIMA on multiple datasets.
We present a neural network technique for the analysis and extrapolation of time-series data called Neural Decomposition (ND). Units with a sinusoidal activation function are used to perform a Fourier-like decomposition of training samples into a sum of sinusoids, augmented by units with nonperiodic activation functions to capture linear trends and other nonperiodic components. We show how careful weight initialization can be combined with regularization to form a simple model that generalizes well. Our method generalizes effectively on the Mackey-Glass series, a dataset of unemployment rates as reported by the U.S. Department of Labor Statistics, a time-series of monthly international airline passengers, the monthly ozone concentration in downtown Los Angeles, and an unevenly sampled time-series of oxygen isotope measurements from a cave in north India. We find that ND outperforms popular time-series forecasting techniques including LSTM, echo state networks, ARIMA, SARIMA, SVR with a radial basis function, and Gashler and Ashmore's model.