Deep Learning Time Series Forecasting
List of state of the art papers focus on deep learning and resources, code and experiments using deep learning for time series forecasting. Classic methods vs Deep Learning methods.
Table of Contents
Papers
2020
-
Tensorized LSTM with Adaptive Shared Memory for Learning Trends in Multivariate Time Series
AAAI 2020
- Dongkuan Xu, et al.
- [Code]
-
RELATIONAL STATE-SPACE MODEL FOR STOCHASTIC MULTI-OBJECT SYSTEMS
ICLR 2020
- Fan Yang, et al.
- Code not yet.
-
For2For: Learning to forecast from forecasts
- Zhao, Shi, et al.
- Code not yet.
2019
-
DSANet: Dual Self-Attention Network for Multivariate Time Series Forecasting
- Siteng Huang, et al.
- Code not yet.
-
Enhancing Time Series Momentum Strategies Using Deep Neural Networks
- Bryan Lim, et al.
- Code not yet.
-
DYNAMIC TIME LAG REGRESSION: PREDICTING WHAT & WHEN
- Mandar Chandorkar, et al.
- Code not yet.
-
Time-series Generative Adversarial Networks
NeurIPS 2019
- Jinsung Yoon. et al.
- Code not yet.
-
Temporal Fusion Transformers for Interpretable Multi-horizon Time Series Forecasting
- Bryan Lim, et al.
Google Research
- [Code]
-
- Vincent Fortuin, et al.
- Code not yet.
-
Deep Physiological State Space Model for Clinical Forecasting
- Yuan Xue, et al.
- not yet
-
AR-Net: A simple Auto-Regressive Neural Network for time-series
- Oskar Triebe, et al.
Facebook Research
- Code not yet.
-
Learning Time-series Data of Industrial Design Optimization using Recurrent Neural Networks
- Sneha Saha, et al.
Honda Research Institute Europe GmbH
- Code not yet.
-
RobustSTL: A Robust Seasonal-Trend Decomposition Algorithm for Long Time Series
- Qingsong Wen, et al.
- [Code]
-
Constructing Gradient Controllable Recurrent Neural Networks Using Hamiltonian Dynamics
- Konstantin Rusch, et al.
- Code not yet.
-
SOM-VAE: Interpretable Discrete Representation Learning on Time Series
ICLR 2019
- Vincent Fortuin, et al.
- [Code]
-
Unsupervised Scalable Representation Learning for Multivariate Time Series
NeurIPS 2019
In Applications -- Time Series Analysis- Jean-Yves Franceschi, et al.
- [Code]
-
Factorized Inference in Deep Markov Models for Incomplete Multimodal Time Series
- Zhi-Xuan Tan, et al.
- Code not yet.
-
You May Not Need Order in Time Series Forecasting
- Yunkai Zhang, et al.
- Code not yet
-
Self-boosted Time-series Forecasting with Multi-task and Multi-view Learning
AAAI 2020
- Long H. Nguyen, et al.
- Code not yet
-
Shape and Time Distortion Loss for Training Deep Time Series Forecasting Models
NeurIPS2019
- Vincent Le Guen and Nicolas Thome.
- [Code]
-
Dynamic Local Regret for Non-convex Online Forecasting
NeurIPS 2019
- Sergul Aydore, et al.
- [Code]
-
Bayesian Temporal Factorization for Multidimensional Time Series Prediction
- Xinyu Chen, and Lijun Sun
- [Code and data]
-
Probabilistic sequential matrix factorization
- Ömer Deniz Akyildiz, et al.
- Code not yet
-
Sequential VAE-LSTM for Anomaly Detection on Time Series
- Run-Qing Chen, et al.
- Code not yet
-
High-Dimensional Multivariate Forecasting with Low-Rank Gaussian Copula Processes
NeurIPS 2019
- David Salinas, et al.
- Code not yet
-
Recurrent Neural Filters: Learning Independent Bayesian Filtering Steps for Time Series Prediction
- Bryan Lim, et al.
- Code not yet
-
- Chengxi Liu, et al.
- Code not yet
-
SKTIME: A UNIFIED INTERFACE FOR MACHINE LEARNING WITH TIME SERIE
- [Code]
-
Recurrent Neural Networks for Time Series Forecasting: Current Status and Future Directions
- [Code]
-
- Antonio Rafael Sabino Parmezan, Vinicius M. A. Souza and Gustavo E. A. P. A. Batista. USP
-
Explainable Deep Neural Networks for Multivariate Time Series Predictions
IJCAI 2019
- Roy Assaf and Anika Schumann. IBM Research, Zurich
- Code not yet
-
Outlier Detection for Time Series with Recurrent Autoencoder Ensembles
IJCAI 2019
- [Code]
-
Learning Interpretable Deep State Space Model for Probabilistic Time Series Forecasting
IJCAI 2019
- Code not yet
-
Deep Factors for Forecasting
ICML 2019
- Code not yet
-
Probabilistic Forecasting with Spline Quantile Function RNNs
- Code not yet
-
Deep learning for time series classification: a review
- Code not yet
-
Multivariate LSTM-FCNs for Time Series Classification
- Code not yet
-
Criteria for classifying forecasting methods
- Code not yet
-
GluonTS: Probabilistic Time Series Models in Python
- [Code]
-
DeepAR: Probabilistic Forecasting with Autoregressive Recurrent Networks
- David Salinas, et al.
- Code not yet
2018
-
Attend and Diagnose: Clinical Time Series Analysis Using Attention Models
AAAI 2018
- Huan Song, Deepta Rajan, et al.
- not yet.
-
Precision and Recall for Time Series
NeurIPS2018
- Nesime Tatbul, et al.
- Code not yet.
-
Deep State Space Models for Time Series Forecasting
NeurIPS2018
- Code not yet
-
Deep Factors with Gaussian Processes for Forecasting
Third workshop on Bayesian Deep Learning (NeurIPS 2018)
- [Code]
-
DIFFUSION CONVOLUTIONAL RECURRENT NEURAL NETWORK: DATA-DRIVEN TRAFFIC FORECASTING
ICLR 2018
- Yaguang Li, et al.
- [Code]
-
DEEP TEMPORAL CLUSTERING: FULLY UNSUPERVISED LEARNING OF TIME-DOMAIN FEATURES
- Naveen Sai Madiraju, et al.
- [Code-unofficial implementation ]
2017
-
Discriminative State-Space Models
NIPS 2017
- Vitaly Kuznetsov and Mehryar Mohri.
- Code not yet.
2016
-
Temporal Regularized Matrix Factorization for High-dimensional Time Series Prediction
NIPS 2016
- [Code]
-
Time Series Prediction and Online Learning
JMLR 2016
- Vitaly Kuznetsov and Mehryar Mohri.
- Code not yet.
Comparative: Classical methods vs Deep Learning methods
-
Forecasting economic and financial time series: ARIMA VS. LSTM
-
A comparative study between LSTM and ARIMA for sales forecasting in retail
-
ARIMA/SARIMA vs LSTM with Ensemble learning Insights for Time Series Data
Conferences
-
Machine learning
-
Artificial intelligence
-
Competitions
Code
Theory-Resource
-
Stock Market Prediction by Recurrent Neural Network on LSTM Model
-
Decoupling Hierarchical Recurrent Neural Networks With Locally Computable Losses
Code-Resource
-
TimeseriesAI: Practical Deep Learning for Time Series / Sequential Data using fastai/ Pytorch.
-
TimescaleDB: An open-source time-series SQL database optimized for fast ingest and complex queries. Packaged as a PostgreSQL extension.
-
Using attentive neural processes for forecasting power usage
-
https://www.kaggle.com/c/recruit-restaurant-visitor-forecasting