Time Series Prediction

Time series prediction aims to forecast future values based on historical data, a crucial task across diverse fields from finance and healthcare to environmental monitoring. Current research emphasizes developing sophisticated models, including transformers, recurrent neural networks (RNNs), and novel hybrid architectures that combine deep learning with traditional statistical methods like ARIMA or wavelet decomposition, to improve accuracy and efficiency, particularly for multivariate and high-dimensional data. These advancements are driving improvements in forecasting accuracy and interpretability, leading to better decision-making in various applications and a deeper understanding of complex temporal dynamics. Furthermore, research is actively exploring methods to enhance uncertainty quantification and communication in predictions, making forecasts more reliable and useful for practical applications.

Papers

April 26, 2022

Time Series Prediction by Multi-task GPR with Spatiotemporal Information Transformation
Peng Tao, Xiaohu Hao, Jie Cheng, Luonan Chen
Temporal Information Time Series Prediction Step Prediction High Dimensional Time Series Spatiotemporal Transformer

March 9, 2022

Monitoring Time Series With Missing Values: a Deep Probabilistic Approach
Oshri Barazani, David Tolpin
Time Series Time Series Forecasting Multivariate Time Series Time Series Prediction Missing Value High Dimensional Time Series Deep Probabilistic Model

March 8, 2022

Sparsification and Filtering for Spatial-temporal GNN in Multivariate Time-series
Yuanrong Wang, Tomaso Aste
Spatio Temporal Multivariate Time Series Time Series Prediction Random Sparsification Spatial Temporal Graph Online Filtering Synthetic Time Series Correlation Graph

March 7, 2022

Automated Few-Shot Time Series Forecasting based on Bi-level Programming
Jiangjiao Xu, Ke Li
Time Series Forecasting Hyperparameter Optimization Bilevel Optimization Time Series Prediction Renewable Energy

March 3, 2022

Early Time-Series Classification Algorithms: An Empirical Comparison
Charilaos Akasiadis, Evgenios Kladis, Evangelos Michelioudakis, Elias Alevizos, Alexander Artikis
Time Series Time Series Prediction Empirical Comparison Algorithm Performance

March 2, 2022

Parallel Spatio-Temporal Attention-Based TCN for Multivariate Time Series Prediction
Fan Jin, Ke Zhang, Yipan Huang, Yifei Zhu, Baiping Chen
Recurrent Neural Network Temporal Attention Temporal Convolutional Network Traditional RNNs Time Series Prediction

February 7, 2022

Structured Time Series Prediction without Structural Prior
Darko Drakulic, Jean-Marc Andreoli
Multivariate Time Series Time Series Prediction Structured Prediction Structural Prior Diffusion Capacity

January 14, 2022

IDEA: Interpretable Dynamic Ensemble Architecture for Time Series Prediction
Mengyue Zha, Kani Chen, Tong Zhang
Time Series Prediction Univariate Time Series Forecasting Interpretable Ensemble Competitive Learning Explainable Ensemble Interpretable Basis

January 6, 2022

Bayesian Regression Approach for Building and Stacking Predictive Models in Time Series Analytics
Bohdan M. Pavlyshenko
Time Series Time Series Prediction Building PCC Time Series Model Integrated Moving Average Stacking Ensemble Bayesian Regression

November 22, 2021

Time Series Prediction about Air Quality using LSTM-Based Models: A Systematic Mapping
Lucas L. S. Sachetti, Vinicius F. S. Mota
Full Model Long Short Term Memory Study Feature Time Series Data Time Series Prediction Air Pollution Systematic Mapping Study Systematic Mapping

Time Series Prediction

Papers

Time Series Prediction by Multi-task GPR with Spatiotemporal Information Transformation

Monitoring Time Series With Missing Values: a Deep Probabilistic Approach

Sparsification and Filtering for Spatial-temporal GNN in Multivariate Time-series

Automated Few-Shot Time Series Forecasting based on Bi-level Programming

Early Time-Series Classification Algorithms: An Empirical Comparison

Parallel Spatio-Temporal Attention-Based TCN for Multivariate Time Series Prediction

Structured Time Series Prediction without Structural Prior

IDEA: Interpretable Dynamic Ensemble Architecture for Time Series Prediction

Bayesian Regression Approach for Building and Stacking Predictive Models in Time Series Analytics

Time Series Prediction about Air Quality using LSTM-Based Models: A Systematic Mapping