BUGATTI633/deep-learning-time-series

List of papers, code and experiments using deep learning for time series forecasting

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, Competitions...

Table of Contents

• Papers
• Conferences
• Competitions
• Code
• Theory-Resource
• Code Resource
• Datasets

Papers

2020

• Zero-shot and few-shot time series forecasting with ordinal regression recurrent neural networks

  • Bernardo Perez Orozco and Stephen J. Roberts.
  • [Code]

• Financial Time Series Representation Learning

  • Philippe Chatigny, et al.
  • Code not yet.

• G-Net: A Deep Learning Approach to G-computation for Counterfactual Outcome Prediction Under Dynamic Treatment Regimes

  • Rui Li, et al.
  • • IBM research and MIT
  • Code not yet.

• Deep Markov Spatio-Temporal Factorization

  • Amirreza Farnoosh, et al.
  • Code not yet.

• Harmonic Recurrent Process for Time Series Forecasting

  • Shao-Qun Zhang and Zhi-Hua Zhou.
  • Code not yet.

• Elastic Machine Learning Algorithms in Amazon SageMaker

  • Edo Liberty, et al.
  • Code not yet.

• Time Series Data Augmentation for Deep Learning: A Survey

  • Qingsong Wen, et al.
  • Code not yet.

• Block Hankel Tensor ARIMA for Multiple Short Time Series ForecastingAAAI 2020

  • QIQUAN SHI, et al.
  • [Code]

• Learnings from Kaggle's Forecasting Competitions

  • Casper Solheim Bojer, et al.
  • Code not yet.

• An Industry Case of Large-Scale Demand Forecasting of Hierarchical Components

  • Rodrigo Rivera-Castro, et al.
  • Code not yet.

• Multi-variate Probabilistic Time Series Forecasting via Conditioned Normalizing Flows

  • Kashif Rasul, et al.
  • [Code].

• ForecastNet: A Time-Variant Deep Feed-Forward Neural Network Architecture for Multi-Step-Ahead Time-Series Forecasting

  • Joel Janek Dabrowski, et al.
  • Code not yet.

• Anomaly detection for Cybersecurity: time series forecasting and deep learningGood review about forecasting

  • Giordano Colò.
  • Code not yet.

• Event-Driven Continuous Time Bayesian Networks

  • Debarun Bhattacharjya, et al.
  • Research AI, IBM
  • Code not yet.

• Joint Modeling of Local and Global Temporal Dynamics for Multivariate Time Series Forecasting with Missing ValuesAAAI 2020

  • Xianfeng Tang, et al.
  • IBM Research, NY
  • Code not yet.

• Topology-Based Clusterwise Regression for User Segmentation and Demand Forecasting

  • Rodrigo Rivera-Castro, et al.
  • Code not yet.

• Evolutionary LSTM-FCN networks for pattern classification in industrial processes

  • Patxi Ortego, et al.
  • Code not yet.

• Forecasting Multivariate Time-Series Data Using LSTM and Mini-Batches

  • Athar Khodabakhsh, et al.
  • Code not yet.

• Tensorized LSTM with Adaptive Shared Memory for Learning Trends in Multivariate Time SeriesAAAI 2020

  • Dongkuan Xu, et al.
  • [Code]

• RELATIONAL STATE-SPACE MODEL FOR STOCHASTIC MULTI-OBJECT SYSTEMSICLR 2020

  • Fan Yang, et al.
  • Code not yet.

• For2For: Learning to forecast from forecasts

  • Zhao, Shi, et al.
  • Code not yet.

2019

• Similarity Preserving Representation Learning for Time Series Clustering

  • Qi Lei, et al.
  • IBM research
  • [Code]

• 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 NetworksNeurIPS 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]

• Deep Amortized Variational Inference for Multivariate Time Series Imputation with Latent Gaussian Process Models

  • 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 SeriesICLR 2019

  • Vincent Fortuin, et al.
  • [Code]

• Unsupervised Scalable Representation Learning for Multivariate Time SeriesNeurIPS 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 ModelsNeurIPS2019

  • Vincent Le Guen and Nicolas Thome.
  • [Code]

• Dynamic Local Regret for Non-convex Online ForecastingNeurIPS 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 ProcessesNeurIPS 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

• LHCnn: A Novel Efficient Multivariate Time Series Prediction Framework Utilizing Convolutional Neural Networks

  • 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]

• Evaluation of statistical and machine learning models for time series prediction: Identifying the state-of-the-art and the best conditions for the use of each model

  • 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 FORECASTINGICLR 2018

  • Yaguang Li, et al.
  • [Code]

• DEEP TEMPORAL CLUSTERING: FULLY UNSUPERVISED LEARNING OF TIME-DOMAIN FEATURES

  • Naveen Sai Madiraju, et al.
  • [Code-unofficial implementation ]

• Modeling Long- and Short-Term Temporal Patterns with Deep Neural Networks

  • Guokun Lai, Wei-Cheng Chang, Yiming Yang, Hanxiao Liu
  • [Code]

2017

• Discriminative State-Space ModelsNIPS 2017

  • Vitaly Kuznetsov and Mehryar Mohri.
  • Code not yet.

2016

• Temporal Regularized Matrix Factorization for High-dimensional Time Series PredictionNIPS 2016

  • [Code]

• Time Series Prediction and Online LearningJMLR 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

  • NeurIPS
  • ICML
  • ICLR

• Artificial intelligence

  • AAAI
  • AISTATS
  • ICANN
  • IJCAI
  • UAI

Competitions

• M5 Competition

Code

• Notebooks
• Code

Theory-Resource

• Deep learning for high dimensional time series-blog

• Deep Learning AI-Optimization

• Backpropagation for LSTM

• Stock Market Prediction by Recurrent Neural Network on LSTM Model

• Decoupling Hierarchical Recurrent Neural Networks With Locally Computable Losses

• Time Series Analysis with Deep Learning : Simplified

• ML techniques applied to stock prices

Code-Resource

• Electric Load Forecasting: Load forecasting on Delhi area electric power load using ARIMA, RNN, LSTM and GRU models.

• Time Series and Forecasting in R

• 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.

• TSstudio: Tools for time series analysis and forecasting

• Prophet: Automatic Forecasting Procedure

• pyts: a Python package for time series classification

• Using attentive neural processes for forecasting power usage

• Non-Gaussian forecasting using fable - R

• SKTIME

• Papers with code - Multivariate time series forecasting

• DeepAR by Amazon

• DFGP by Amazon

• https://www.kaggle.com/c/demand-forecasting-kernels-only

• https://www.kaggle.com/c/favorita-grocery-sales-forecasting

• https://www.kaggle.com/c/grupo-bimbo-inventory-demand

• https://www.kaggle.com/c/recruit-restaurant-visitor-forecasting

• Predicting/hypothesizing the findings of the M4 Competition

Datasets

• Electricity dataset from UCI

• Traffic dataset from UCI

• Air quality from UCI

• Seattle freeway traffic speed

• Kaggle-Web Traffic Time Series Forecasting