Time series analytics plays an important role in a wide range of real-life problems containing temporal components. Deep learning techniques have an effective and important role in solving time series forecasting problems. It can handle multiple input variables, support multivariate inputs, complex nonlinear relationships, and may not require a scaled or stationary time series as input. Multi-layer Perceptron (MLP), Convolutional Neural Network (CNN), Recurrent Neural Network (RNN), Long Short Term Neural Network (LSTM), Gated Recurrent Unit (GRU), Encoder-Decoder model, and Attention mechanism are the deep learning architectures for time series analysis.
The application areas of Deep Learning for time series prediction are weather forecasting, economic forecasting, financial analysis, pattern recognition, healthcare, anomaly detection, and many more. Future advancements of time series predictions are Highly Scalable Autonomous Time Series Analysis, Time-series classification for new-generation Earth observation satellites, Efficient and effective analytics for real-world time series forecasting, Adaptive time-variant models for fuzzy-time-series forecasting, and Automated time series forecasting for bio-surveillance.