SOTAVerified

Time Series Analysis

Time Series Analysis is a statistical technique used to analyze and model time-based data. It is used in various fields such as finance, economics, and engineering to analyze patterns and trends in data over time. The goal of time series analysis is to identify the underlying patterns, trends, and seasonality in the data, and to use this information to make informed predictions about future values.

( Image credit: Autoregressive CNNs for Asynchronous Time Series )

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 51–100 of 6748 papers

TitleStatusHype
Multi-Patch Prediction: Adapting LLMs for Time Series Representation LearningCode2
MOMENT: A Family of Open Time-series Foundation ModelsCode2
Position: What Can Large Language Models Tell Us about Time Series AnalysisCode2
Minusformer: Improving Time Series Forecasting by Progressively Learning ResidualsCode2
Spatial-Temporal Large Language Model for Traffic PredictionCode2
A Survey on Graph Neural Networks for Time Series: Forecasting, Classification, Imputation, and Anomaly DetectionCode2
FITS: Modeling Time Series with 10k ParametersCode2
Self-Supervised Learning for Time Series Analysis: Taxonomy, Progress, and ProspectsCode2
PyPOTS: A Python Toolbox for Data Mining on Partially-Observed Time SeriesCode2
Model scale versus domain knowledge in statistical forecasting of chaotic systemsCode2
One Fits All:Power General Time Series Analysis by Pretrained LMCode2
JANA: Jointly Amortized Neural Approximation of Complex Bayesian ModelsCode2
MTS-Mixers: Multivariate Time Series Forecasting via Factorized Temporal and Channel MixingCode2
A Survey on Deep Learning based Time Series Analysis with Frequency TransformationCode2
LogAI: A Library for Log Analytics and IntelligenceCode2
Salesforce CausalAI Library: A Fast and Scalable Framework for Causal Analysis of Time Series and Tabular DataCode2
PDFormer: Propagation Delay-Aware Dynamic Long-Range Transformer for Traffic Flow PredictionCode2
Synthcity: facilitating innovative use cases of synthetic data in different data modalitiesCode2
ViTs for SITS: Vision Transformers for Satellite Image Time SeriesCode2
Generative Time Series Forecasting with Diffusion, Denoise, and DisentanglementCode2
Towards Long-Term Time-Series Forecasting: Feature, Pattern, and DistributionCode2
End-to-End Modeling Hierarchical Time Series Using Autoregressive Transformer and Conditional Normalizing Flow based ReconciliationCode2
SatlasPretrain: A Large-Scale Dataset for Remote Sensing Image UnderstandingCode2
Liquid Structural State-Space ModelsCode2
Diffusion-based Time Series Imputation and Forecasting with Structured State Space ModelsCode2
Self-supervised Contrastive Representation Learning for Semi-supervised Time-Series ClassificationCode2
Spatial-Temporal Identity: A Simple yet Effective Baseline for Multivariate Time Series ForecastingCode2
Learning Deep Time-index Models for Time Series ForecastingCode2
HierarchicalForecast: A Reference Framework for Hierarchical Forecasting in PythonCode2
Pre-training Enhanced Spatial-temporal Graph Neural Network for Multivariate Time Series ForecastingCode2
Decoupled Dynamic Spatial-Temporal Graph Neural Network for Traffic ForecastingCode2
Self-Supervised Contrastive Pre-Training For Time Series via Time-Frequency ConsistencyCode2
OmniXAI: A Library for Explainable AICode2
Non-stationary Transformers: Exploring the Stationarity in Time Series ForecastingCode2
An Extensive Data Processing Pipeline for MIMIC-IVCode2
Satellite Image Time Series Analysis for Big Earth Observation DataCode2
Attention-based CNN-LSTM and XGBoost hybrid model for stock predictionCode2
Domino: Discovering Systematic Errors with Cross-Modal EmbeddingsCode2
ADATIME: A Benchmarking Suite for Domain Adaptation on Time Series DataCode2
Flowformer: Linearizing Transformers with Conservation FlowsCode2
TTS-GAN: A Transformer-based Time-Series Generative Adversarial NetworkCode2
CoST: Contrastive Learning of Disentangled Seasonal-Trend Representations for Time Series ForecastingCode2
ETSformer: Exponential Smoothing Transformers for Time-series ForecastingCode2
FEDformer: Frequency Enhanced Decomposed Transformer for Long-term Series ForecastingCode2
N-HiTS: Neural Hierarchical Interpolation for Time Series ForecastingCode2
Unifying Pairwise Interactions in Complex DynamicsCode2
TranAD: Deep Transformer Networks for Anomaly Detection in Multivariate Time Series DataCode2
NeuralProphet: Explainable Forecasting at ScaleCode2
LibCity: An Open Library for Traffic PredictionCode2
Anomaly Transformer: Time Series Anomaly Detection with Association DiscrepancyCode2
Show:102550
← PrevPage 2 of 135Next →
All datasetsPhysioNet Challenge 2012Speech CommandsVentilator Pressure Prediction

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1naive classifierF187.47—Unverified
2GRU-D - APC (n = 1)F127.3—Unverified
3GRU-APC (n = 1)F125.7—Unverified
4GRU-DF122.5—Unverified
5GRUF122.3—Unverified
6GRU-SimpleF122.2—Unverified
7GRU-MeanF122.1—Unverified
#ModelMetricClaimedVerifiedStatus
1SepTr% Test Accuracy98.51—Unverified
2ViT% Test Accuracy98.11—Unverified
3FlexTCN-4% Test Accuracy97.73—Unverified
4MatchboxNet% Test Accuracy97.4—Unverified
5CKCNN (100k)% Test Accuracy95.27—Unverified
6FlexTCN-6% Test Accuracy (Raw Data)91.73—Unverified
#ModelMetricClaimedVerifiedStatus
1ResBiLSTMMAE0.13—Unverified