Probabilistic Forecasting with Temporal Convolutional Neural Network
By Yitian Chen, Yanfei Kang, Yixiong Chen, Zizhuo Wang. Neurocomputing, 2019
405 citations recorded by the source corpus.
We present a probabilistic forecasting framework based on convolutional neural network for multiple related time series forecasting. The framework can be applied to estimate probability density under both parametric and non-parametric settings. More specifically, stacked residual blocks based on dilated causal convolutional nets are constructed to capture the temporal dependencies of the series. Combined with representation learning, our approach is able to learn complex patterns such as seasonality, holiday effects within and across series, and to leverage those patterns for more accurate forecasts, especially when historical data is sparse or unavailable. Extensive empirical studies are performed on several real-world datasets, including datasets from this http URL, China's largest online retailer. The results show that our framework outperforms other state-of-the-art methods in both accuracy and efficiency.
Subfields: Management Science and Operations Research, Signal Processing
View Paper: https://www.semanticscholar.org/paper/7962d2e40c97a6435ae410bfb26ddd3801557909
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Management Science and Operations Research
- Fotios Petropoulos
- Rob J Hyndman
- Konstantinos Nikolopoulos
- Nikolaos Kourentzes
- Vassilios Assimakopoulos
- Spyros Makridakis
- Evangelos Spiliotis
- Christoph Bergmeir
In Signal Processing
- Bernie Wang
- Tim Januschowski
- Jan Gasthaus
- Vassilios Assimakopoulos
- Konstantinos Nikolopoulos
- Evangelos Spiliotis
- Spyros Makridakis
- Fotios Petropoulos
Citations in the corpus
- Deep Learning for Time Series Forecasting: A Survey (2020, neutral): “182,189,190,192 However, any of the other network architectures can be applied to time series of miscellaneous application domains not classified in Table 6.”
- Deep Learning for Time Series Forecasting: Tutorial and Literature Survey (2020, methodology): “DeepTCN [35] CNN + MLP Prob ≥1 QL QL retail demand Learns pre-specified grid of quantiles .”
- Temporal Convolutional Networks Applied to Energy-Related Time Series Forecasting (2020, methodology): “[26] designed a deep TCN for multiple related time series with an encoder–decoder scheme, evaluating over data from the sales domain; the study in [27] proposed a multivariate time series forecasting model for meteorological data, which outperformed several popular deep learning models.”
- Forecasting: theory and practice (2020, background): “(2009) who introduce a robust version of the exponential and Holt-Winters smoothing technique for prediction purposes and by Cheng and Yang (2015) who propose an outlier resistant algorithm developed starting from a new synthetic loss function.”