About
The goal of Time Series Prediction is to infer the future values of a time series from the past.
Source: Orthogonal Echo State Networks and stochastic evaluations of likelihoods
Benchmarks
| TREND | DATASET | BEST METHOD | PAPER TITLE | PAPER | CODE | COMPARE |
|---|---|---|---|---|---|---|
|
Datasets
Greatest papers with code
GluonTS: Probabilistic Time Series Models in Python
• awslabs/gluon-ts
• 
We introduce Gluon Time Series (GluonTS, available at https://gluon-ts. mxnet. io), a library for deep-learning-based time series modeling.
ANOMALY DETECTION TIME SERIES TIME SERIES FORECASTING TIME SERIES PREDICTION
Liquid Time-constant Networks
We introduce a new class of time-continuous recurrent neural network models.
Adaptive Graph Convolutional Recurrent Network for Traffic Forecasting
NeurIPS 2020
• benedekrozemberczki/pytorch_geometric_temporal
• 
We further propose an Adaptive Graph Convolutional Recurrent Network (AGCRN) to capture fine-grained spatial and temporal correlations in traffic series automatically based on the two modules and recurrent networks.
Ranked #2 on
Traffic Prediction
on PeMS04
GRAPH GENERATION MULTIVARIATE TIME SERIES FORECASTING SPATIO-TEMPORAL FORECASTING TIME SERIES TIME SERIES PREDICTION TRAFFIC PREDICTION
Diffusion Convolutional Recurrent Neural Network: Data-Driven Traffic Forecasting
ICLR 2018
• benedekrozemberczki/pytorch_geometric_temporal
•
Spatiotemporal forecasting has various applications in neuroscience, climate and transportation domain.
Ranked #3 on
Traffic Prediction
on PeMS-M
MULTIVARIATE TIME SERIES FORECASTING SPATIO-TEMPORAL FORECASTING TIME SERIES TIME SERIES PREDICTION TRAFFIC PREDICTION
Bayesian Temporal Factorization for Multidimensional Time Series Prediction
In this paper, we propose a Bayesian temporal factorization (BTF) framework for modeling multidimensional time series -- in particular spatiotemporal data -- in the presence of missing values.
Low-Rank Autoregressive Tensor Completion for Multivariate Time Series Forecasting
In this paper, we propose a low-rank autoregressive tensor completion (LATC) framework to model multivariate time series data.
IMPUTATION MULTIVARIATE TIME SERIES FORECASTING TIME SERIES TIME SERIES PREDICTION
A Dual-Stage Attention-Based Recurrent Neural Network for Time Series Prediction
• AIStream-Peelout/flow-forecast
•
The Nonlinear autoregressive exogenous (NARX) model, which predicts the current value of a time series based upon its previous values as well as the current and past values of multiple driving (exogenous) series, has been studied for decades.
Spatio-Temporal Graph Convolutional Networks: A Deep Learning Framework for Traffic Forecasting
Timely accurate traffic forecast is crucial for urban traffic control and guidance.
Ranked #4 on
Traffic Prediction
on PeMS-M
Legendre Memory Units: Continuous-Time Representation in Recurrent Neural Networks
NeurIPS 2019
• abr/neurips2019
• 
Backpropagation through the ODE solver allows each layer to adapt its internal time-step, enabling the network to learn task-relevant time-scales.
Ranked #6 on
Sequential Image Classification
on Sequential MNIST
SEQUENTIAL IMAGE CLASSIFICATION TIME SERIES TIME SERIES PREDICTION
Recurrent Neural Networks for Multivariate Time Series with Missing Values
• Han-JD/GRU-D
•
Multivariate time series data in practical applications, such as health care, geoscience, and biology, are characterized by a variety of missing values.
Ranked #4 on
Multivariate Time Series Forecasting
on MuJoCo
MULTIVARIATE TIME SERIES FORECASTING MULTIVARIATE TIME SERIES IMPUTATION TIME SERIES TIME SERIES ANALYSIS TIME SERIES CLASSIFICATION TIME SERIES PREDICTION