Corpus ID: 36367927

Conditional Time Series Forecasting with Convolutional Neural Networks

@article{Borovykh2017ConditionalTS,
  title={Conditional Time Series Forecasting with Convolutional Neural Networks},
  author={Anastasia Borovykh and Sander M. Boht{\'e} and Cornelis W. Oosterlee},
  journal={arXiv: Machine Learning},
  year={2017}
}
textabstractForecasting financial time series using past observations has been a significant topic of interest. [...] Key Method Effectively, we use multiple financial time series as input in the neural network, thus conditioning the forecast of a time series x(t) on both its own history as well as that of a second (or third) time series y(t). Training a model on multiple stock series allows the network to exploit the correlation structure between these series so that the network can learn the market dynamics…Expand
Forecasting Financial Time Series through Causal and Dilated Convolutional Neural Networks
TLDR
In this paper, predictions of future price movements of a major American stock index were made by analyzing past movements of the same and other correlated indices by modifying a model modified to suit the analysis of financial data. Expand
The Effectiveness of Discretization in Forecasting: An Empirical Study on Neural Time Series Models
TLDR
It is found that binning almost always improves performance (compared to using normalized real-valued inputs), but that the particular type of binning chosen is of lesser importance. Expand
Conditional mutual information-based contrastive loss for financial time series forecasting
TLDR
This paper proposes to first learn compact representations from time series data, then use the learned representations to train a simpler model for predicting time series movements, and considers a class-conditioned latent variable model. Expand
Improving the Accuracy of Global Forecasting Models using Time Series Data Augmentation
TLDR
This study proposes a novel, data augmentation based forecasting framework that is capable of improving the baseline accuracy of the GFM models in less data-abundant settings and can outperform state-of-the-art univariate forecasting methods. Expand
Time Series is a Special Sequence: Forecasting with Sample Convolution and Interaction
TLDR
Compared to conventional dilated causal convolution architectures, the proposed downsample-convolve-interact architecture enables multi-resolution analysis besides expanding the receptive field of the convolution operation, which facilitates extracting temporal relation features with enhanced predictability. Expand
MegazordNet: combining statistical and machine learning standpoints for time series forecasting
TLDR
The MegazordNet is proposed, a framework that explores statistical features within a financial series combined with a structured deep learning model for time series forecasting that was able to beat single statistical and machine learning methods. Expand
Multi-step Deep Autoregressive Forecasting with Latent States
In many forecasting applications, it is important to predict an overall trajectory within a period of time, i.e. a forecasting horizon. Various deep neural network models have been introduced toExpand
Probabilistic Forecasting with Temporal Convolutional Neural Network
TLDR
A probabilistic forecasting framework based on convolutional neural network for multiple related time series forecasting that outperforms other state-of-the-art methods in both accuracy and efficiency. Expand
AR-Net: A simple Auto-Regressive Neural Network for time-series
TLDR
A new framework for time-series modeling that combines the best of traditional statistical models and neural networks is presented, and it is shown that AR-Net is as interpretable as Classic-AR but also scales to long-range dependencies. Expand
Comparative Analysis of Deep Learning Models for Multi-Step Prediction of Financial Time Series
TLDR
Experimental results show that the latest deep learning models such as N-BEATS, ES-LSTM and TCN produced better results for all stock market related datasets by obtaining around 50% less Root Mean Squared Error (RMSE) and Mean Absolute Error (MAE) scores for each prediction horizon as compared to other models. Expand
...
1
2
3
4
5
...

References

SHOWING 1-10 OF 29 REFERENCES
Multi-period Time Series Modeling with Sparsity via Bayesian Variational Inference
In this paper, we use augmented the hierarchical latent variable model to model multi-period time series, where the dynamics of time series are governed by factors or trends in multiple periods.Expand
Autoregressive Convolutional Neural Networks for Asynchronous Time Series
TLDR
The model is inspired by standard autoregressive models and gating mechanisms used in recurrent neural networks and involves an AR-like weighting system, where the final predictor is obtained as a weighted sum of adjusted regressors, while the weights are datadependent functions learnt through a convolutional network. Expand
Combining Neural Network Forecasts on Wavelet-transformed Time Series
We discuss a simple strategy aimed at improving neural network prediction accuracy, based on the combination of predictions at varying resolution levels of the domain under investigation (here: timeExpand
Time Series Forecasting Based on Augmented Long Short-Term Memory
TLDR
Recurrent autoencoder model is used to predict the time series in single and multiple steps ahead and significantly improves the state-of-art performance on chaotic time series benchmark and also has better performance on real-world data. Expand
Time-series modeling with undecimated fully convolutional neural networks
TLDR
A fully convolutional network (FCN) architecture that uses causal filtering operations, and allows for the rate of the output signal to be the same as that of the input signal, is considered, which has several advantages compared to other time-series models such as the recurrent neural network and long short-term memory. Expand
Deep learning with long short-term memory networks for financial market predictions
TLDR
This work deploys LSTM networks for predicting out-of-sample directional movements for the constituent stocks of the S&P 500 from 1992 until 2015 and finds one common pattern among the stocks selected for trading – they exhibit high volatility and a short-term reversal return profile. Expand
Forecasting the behavior of multivariate time series using neural networks
TLDR
The results show that the neural network approach to multivariate time-series analysis is a leading contender with the statistical modeling approaches. Expand
Wavelet low- and high-frequency components as features for predicting stock prices with backpropagation neural networks
  • S. Lahmiri
  • Computer Science
  • J. King Saud Univ. Comput. Inf. Sci.
  • 2014
TLDR
A forecasting model that integrates the discrete wavelet transform (DWT) and backpropagation neural networks (BPNN) for predicting financial time series outperforms both the well-known auto-regressive moving-average (ARMA) model and the random walk (RW) process. Expand
Time series classification from scratch with deep neural networks: A strong baseline
TLDR
The proposed Fully Convolutional Network (FCN) achieves premium performance to other state-of-the-art approaches and the exploration of the very deep neural networks with the ResNet structure is also competitive. Expand
Exploiting multi-channels deep convolutional neural networks for multivariate time series classification
TLDR
A novel deep learning framework, multi-channels deep convolutional neural networks (MC-DCNN), for multivariate time series classification, which is not only more efficient than the state of the art but also competitive in accuracy. Expand
...
1
2
3
...