Conditional Time Series Forecasting with Convolutional Neural Networks
arXiv:1703.04691
Abstract
We present a method for conditional time series forecasting based on an adaptation of the recent deep convolutional WaveNet architecture. The proposed network contains stacks of dilated convolutions that allow it to access a broad range of history when forecasting, a ReLU activation function and conditioning is performed by applying multiple convolutional filters in parallel to separate time series which allows for the fast processing of data and the exploitation of the correlation structure between the multivariate time series. We test and analyze the performance of the convolutional network both unconditionally as well as conditionally for financial time series forecasting using the S&P500, the volatility index, the CBOE interest rate and several exchange rates and extensively compare it to the performance of the well-known autoregressive model and a long-short term memory network. We show that a convolutional network is well-suited for regression-type problems and is able to effectively learn dependencies in and between the series without the need for long historical time series, is a time-efficient and easy to implement alternative to recurrent-type networks and tends to outperform linear and recurrent models.
References in corpus (4)
Cited by in corpus (54)
- Time Series Forecasting With Deep Learning: A Survey
- Recurrent Neural Networks for Time Series Forecasting: Current Status and Future Directions
- Enhancing the Locality and Breaking the Memory Bottleneck of Transformer on Time Series Forecasting
- Adaptive Graph Convolutional Recurrent Network for Traffic Forecasting
- Autoformer: Decomposition Transformers with Auto-Correlation for Long-Term Series Forecasting
- Deep Learning for Time Series Forecasting: Tutorial and Literature Survey
- A Multi-Horizon Quantile Recurrent Forecaster
- SCINet: Time Series Modeling and Forecasting with Sample Convolution and Interaction
- LSTM-MSNet: Leveraging Forecasts on Sets of Related Time Series with Multiple Seasonal Patterns
- Anomaly Detection in Univariate Time-series: A Survey on the State-of-the-Art
- Kolmogorov-Arnold Networks (KANs) for Time Series Analysis
- Think Globally, Act Locally: A Deep Neural Network Approach to High-Dimensional Time Series Forecasting
- Autoregressive Convolutional Neural Networks for Asynchronous Time Series
- Long-Range Transformers for Dynamic Spatiotemporal Forecasting
- Model-based Deep Reinforcement Learning for Dynamic Portfolio Optimization
- AR-Net: A simple Auto-Regressive Neural Network for time-series
- Bayesian neural networks via MCMC: a Python-based tutorial
- Multivariate Time Series Classification using Dilated Convolutional Neural Network
- LAVARNET: Neural Network Modeling of Causal Variable Relationships for Multivariate Time Series Forecasting
- Probabilistic Forecasting with Temporal Convolutional Neural Network
- Deep reinforcement learning for time series: playing idealized trading games
- Domain Adaptation for Time Series Forecasting via Attention Sharing
- Differential Convolutional Fuzzy Time Series Forecasting
- A Gaussian Process perspective on Convolutional Neural Networks
- Neural Forecasting of the Italian Sovereign Bond Market with Economic News
- Long Horizon Forecasting With Temporal Point Processes
- Surrogate Optimization of Deep Neural Networks for Groundwater Predictions
- Series Saliency: Temporal Interpretation for Multivariate Time Series Forecasting
- Hierarchically Regularized Deep Forecasting
- A Two-Step Framework for Arbitrage-Free Prediction of the Implied Volatility Surface
- The Effectiveness of Discretization in Forecasting: An Empirical Study on Neural Time Series Models
- QDCNN: Quantum Dilated Convolutional Neural Network
- Self-boosted Time-series Forecasting with Multi-task and Multi-view Learning
- Time Distributed Deep Learning Models for Purely Exogenous Forecasting: Application to Water Table Depth Prediction using Weather Image Time Series
- Data-Driven Vehicle Trajectory Forecasting
- SincVAE: A new semi-supervised approach to improve anomaly detection on EEG data using SincNet and variational autoencoder
- Conditional Generation of Periodic Signals with Fourier-Based Decoder
- A multi-series framework for demand forecasts in E-commerce
- Conditional Mutual information-based Contrastive Loss for Financial Time Series Forecasting
- Precipitation Nowcasting: Leveraging bidirectional LSTM and 1D CNN
- A Spatio-temporal Prediction Methodology Based on Deep Learning and Real Wi-Fi Measurements
- Reconstructing a dynamical system and forecasting time series by self-consistent deep learning
- Discovering Predictable Latent Factors for Time Series Forecasting
- ShortFuse: Biomedical Time Series Representations in the Presence of Structured Information
- Neural Networks for Lorenz Map Prediction: A Trip Through Time
- Deep convolutional autoencoder for cryptocurrency market analysis
- Optimizing Hyperparameters in CNNs using Bilevel Programming in Time Series Data
- How to Teach a Quantum Computer a Probability Distribution
- Corn Yield Prediction with Ensemble CNN-DNN
- Single Model for Influenza Forecasting of Multiple Countries by Multi-task Learning
- Volatility Forecasting with 1-dimensional CNNs via transfer learning
- MegazordNet: combining statistical and machine learning standpoints for time series forecasting
- Cluster-and-Conquer: A Framework For Time-Series Forecasting
- Interpretability in Safety-Critical FinancialTrading Systems