Dynamic prediction length for time series with sequence to sequence network
Article No.: 4, Pages 1 - 9
Abstract
Recurrent neural networks and sequence to sequence models require a predetermined length for prediction output length. Our model addresses this by allowing the network to predict a variable length output in inference. A new loss function with a tailored gradient computation is developed that trades off prediction accuracy and output length. The model utilizes a function to determine whether a particular output at a time should be evaluated or not given a predetermined threshold. We evaluate the model on the problem of predicting the prices of securities. We find that the model makes longer predictions for more stable securities and it naturally balances prediction accuracy and length.
References
[1]
Ryo Akita, Akira Yoshihara, Takashi Matsubara, and Kuniaki Uehara. 2016. Deep learning for stock prediction using numerical and textual information. In 15th International Conference on Computer and Information Science. 1--6.
[2]
Martin Arjovsky, Soumith Chintala, and Léon Bottou. 2017. Wasserstein GAN. arXiv preprint arXiv:1701.07875 (2017).
[3]
Dzmitry Bahdanau, Kyunghyun Cho, and Yoshua Bengio. 2014. Neural machine translation by jointly learning to align and translate. arXiv preprint arXiv:1409.0473 (2014).
[4]
Wei Bao, Jun Yue, and Yulei Rao. 2017. A deep learning framework for financial time series using stacked autoencoders and long-short term memory. PLOS ONE 7 (2017).
[5]
Anastasia Borovykh, Sander Bohte, and Cornelis W Oosterlee. 2017. Conditional time series forecasting with convolutional neural networks. arXiv preprint arXiv:1703.04691 (2017).
[6]
Kai Chen, Yi Zhou, and Fangyan Dai. 2015. A LSTM-based method for stock returns prediction: A case study of China stock market. In IEEE International Conference on Big Data. 2823--2824.
[7]
Eunsuk Chong, Chulwoo Han, and Frank C Park. 2017. Deep learning networks for stock market analysis and prediction: Methodology, data representations, and case studies. Expert Systems with Applications (2017), 187--205.
[8]
Xiao Ding, Yue Zhang, Ting Liu, and Junwen Duan. 2015. Deep Learning for Event-Driven Stock Prediction. In Twenty-Fourth International Joint Conference on Artificial Intelligence.
[9]
Matthew Dixon, Diego Klabjan, and Jin Hoon Bang. 2016. Classification-based financial markets prediction using deep neural networks. Algorithmic Finance Preprint (2016), 1--11.
[10]
Charlie Frogner, Chiyuan Zhang, Hossein Mobahi, Mauricio Araya, and Tomaso A Poggio. 2015. Learning with a Wasserstein loss. In Advances in Neural Information Processing Systems. 2053--2061.
[11]
Alex Graves. 2016. Adaptive computation time for recurrent neural networks. arXiv preprint arXiv:1603.08983 (2016).
[12]
Alex Graves, Greg Wayne, and Ivo Danihelka. 2014. Neural turing machines. arXiv preprint arXiv:1410.5401 (2014).
[13]
Kaiming He, Xiangyu Zhang, Shaoqing Ren, and Jian Sun. 2016. Deep residual learning for image recognition. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 770--778.
[14]
Katarzyna Janocha, Wojciech Marian Czarnecki, et al. 2017. On loss functions for deep neural networks in classification. Schedae Informaticae 2016 (2017), 4959.
[15]
Diederik P Kingma and Jimmy Ba. 2014. Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014).
[16]
Christopher Krauss, Xuan Anh Do, and Nicolas Huck. 2017. Deep neural networks, gradient-boosted trees, random forests: Statistical arbitrage on the S&P 500. European Journal of Operational Research 2 (2017), 689--702.
[17]
Seyed Taghi Akhavan Niaki and Saeid Hoseinzade. 2013. Forecasting S&P 500 index using artificial neural networks and design of experiments. Journal of Industrial Engineering International 1 (2013), 1.
[18]
Justin A Sirignano. 2016. Deep Learning for Limit Order Books. arXiv preprint arXiv:1601.01987 (2016).
[19]
Sainbayar Sukhbaatar, Jason Weston, Rob Fergus, et al. 2015. End-to-end memory networks. In Advances in Neural Information Processing Systems. 2440--2448.
[20]
Ilya Sutskever, Oriol Vinyals, and Quoc V Le. 2014. Sequence to sequence learning with neural networks. In Advances in Neural Information Processing Systems. 3104--3112.
[21]
Oriol Vinyals, Meire Fortunato, and Navdeep Jaitly. 2015. Pointer networks. In Advances in Neural Information Processing Systems. 2692--2700.
[22]
Shi Xingjian, Zhourong Chen, Hao Wang, Dit-Yan Yeung, Wai-Kin Wong, and Wang-chun Woo. 2015. Convolutional LSTM network: A machine learning approach for precipitation nowcasting. In Advances in Neural Information Processing Systems. 802--810.
Index Terms
- Dynamic prediction length for time series with sequence to sequence network
Recommendations
Time Series Prediction Method Based on Variant LSTM Recurrent Neural Network
AbstractTime series prediction problems are a difficult type of predictive modeling problem. In this paper, we propose a time series prediction method based on a variant long short-term memory (LSTM) recurrent neural network. In the proposed method, we ...
Multistep-Ahead Prediction of Time Series Using Independent Models
ICEICE '12: Proceedings of the 2012 Second International Conference on Electric Information and Control Engineering - Volume 02Multi step-ahead prediction of time series is widely used in real applications, such as finance, transportation and electrical load. A multi step-ahead independent prediction approach of time series is proposed. The step-by-step recurrent approach and ...
Prediction of chaotic time series based on the recurrent predictor neural network
Chaos limits predictability so that the long-term prediction of chaotic time series is very difficult. The main purpose of this paper is to study a new methodology to model and predict chaotic time series based on a new recurrent predictor neural ...
Comments
Information & Contributors
Information
Published In
Copyright © 2020 ACM.
Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than ACM must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from [email protected]
Sponsors
Publisher
Association for Computing Machinery
New York, NY, United States
Publication History
Published: 07 October 2021
Check for updates
Author Tags
Qualifiers
- Research-article
Conference
ICAIF '20
Sponsor:
Contributors
Other Metrics
Bibliometrics & Citations
Bibliometrics
Article Metrics
- 0Total Citations
- 103Total Downloads
- Downloads (Last 12 months)16
- Downloads (Last 6 weeks)2
Reflects downloads up to 03 Mar 2025
Other Metrics
Citations
View Options
Login options
Check if you have access through your login credentials or your institution to get full access on this article.
Sign in