Time Series

943 papers with code • 3 benchmarks • 4 datasets

Time series deals with sequential data where the data is indexed (ordered) by a time dimension.

( Image credit: Autoregressive CNNs for Asynchronous Time Series )

Greatest papers with code

Temporal Fusion Transformers for Interpretable Multi-horizon Time Series Forecasting

google-research/google-research 19 Dec 2019

Multi-horizon forecasting problems often contain a complex mix of inputs -- including static (i. e. time-invariant) covariates, known future inputs, and other exogenous time series that are only observed historically -- without any prior information on how they interact with the target.

Interpretable Machine Learning Time Series +1

Diverse Beam Search: Decoding Diverse Solutions from Neural Sequence Models

pytorch/fairseq 7 Oct 2016

We observe that our method consistently outperforms BS and previously proposed techniques for diverse decoding from neural sequence models.

Image Captioning Machine Translation +3

Distributed and parallel time series feature extraction for industrial big data applications

blue-yonder/tsfresh 25 Oct 2016

This problem is especially hard to solve for time series classification and regression in industrial applications such as predictive maintenance or production line optimization, for which each label or regression target is associated with several time series and meta-information simultaneously.

Feature Importance Feature Selection +3

Stock Price Prediction via Discovering Multi-Frequency Trading Patterns

microsoft/qlib 13 Aug 2017

Then the future stock prices are predicted as a nonlinear mapping of the combination of these components in an Inverse Fourier Transform (IFT) fashion.

Stock Price Prediction Time Series

Applications of Deep Neural Networks

jeffheaton/t81_558_deep_learning 11 Sep 2020

Through a combination of advanced training techniques and neural network architectural components, it is now possible to create neural networks that can handle tabular data, images, text, and audio as both input and output.

Time Series

Stochastic Weight Matrix-based Regularization Methods for Deep Neural Networks

pytorch/ignite 26 Sep 2019

The aim of this paper is to introduce two widely applicable regularization methods based on the direct modification of weight matrices.

Time Series

Adversarial Robustness Toolbox v1.0.0

IBM/adversarial-robustness-toolbox 3 Jul 2018

Defending Machine Learning models involves certifying and verifying model robustness and model hardening with approaches such as pre-processing inputs, augmenting training data with adversarial samples, and leveraging runtime detection methods to flag any inputs that might have been modified by an adversary.

Gaussian Processes Time Series

Spliced Binned-Pareto Distribution for Robust Modeling of Heavy-tailed Time Series

awslabs/gluon-ts 21 Jun 2021

This work proposes a novel method to robustly and accurately model time series with heavy-tailed noise, in non-stationary scenarios.

Anomaly Detection Time Series

GluonTS: Probabilistic Time Series Models in Python

awslabs/gluon-ts 12 Jun 2019

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 +2

Efficient Matrix Profile Computation Using Different Distance Functions

TDAmeritrade/stumpy 17 Jan 2019

The results also show that the ACAMP algorithm is significantly faster than SCRIMP++ (the state of the art matrix profile algorithm) for the case of z-normalized Euclidean distance.

Time Series