Time Series Forecasting

Time series forecasting aims to predict future values based on historical data, crucial for diverse applications from finance to healthcare. Current research emphasizes improving model accuracy and efficiency, focusing on transformer-based architectures, state-space models like Mamba, and hybrid approaches combining their strengths, as well as exploring data augmentation and explainable AI techniques. These advancements are driving improvements in forecasting accuracy and interpretability, leading to better decision-making across various sectors and contributing to a deeper understanding of complex temporal dynamics.

Papers

April 11, 2023

Financial Time Series Forecasting using CNN and Transformer
Zhen Zeng, Rachneet Kaur, Suchetha Siddagangappa, Saba Rahimi, Tucker Balch, Manuela Veloso
Deep Learning Convolutional Neural Network Transformer Based Time Series Forecasting Temporal Dependency Financial Time Series

April 10, 2023

Two Steps Forward and One Behind: Rethinking Time Series Forecasting with Deep Learning
Riccardo Ughi, Eugenio Lomurno, Matteo Matteucci
Deep Learning Transformer Based Transformer Based Model Time Series Forecasting Long Term Time Series Forecasting

April 9, 2023

Ensemble Modeling for Time Series Forecasting: an Adaptive Robust Optimization Approach
Dimitris Bertsimas, Leonard Boussioux
Time Series Forecasting Robust Optimization Ensemble Model Robust Ensemble Adaptive Ensemble Tropical Cyclone Intensity

April 8, 2023

OFTER: An Online Pipeline for Time Series Forecasting
Nikolas Michael, Mihai Cucuringu, Sam Howison
Time Series Forecasting Forecasting Pipeline

March 31, 2023

SimTS: Rethinking Contrastive Representation Learning for Time Series Forecasting
Xiaochen Zheng, Xingyu Chen, Manuel Schürch, Amina Mollaysa, Ahmed Allam, Michael Krauthammer
Contrastive Learning Time Series Forecasting Contrastive Representation Learning Forecasting Benchmark

March 24, 2023

Towards Diverse and Coherent Augmentation for Time-Series Forecasting
Xiyuan Zhang, Ranak Roy Chowdhury, Jingbo Shang, Rajesh Gupta, Dezhi Hong
Data Augmentation Time Series Time Series Forecasting Time Series Data Diverse Set Self Augmentation Real World Time Series Time Augmentation

March 22, 2023

TsSHAP: Robust model agnostic feature-based explainability for time series forecasting
Vikas C. Raykar, Arindam Jati, Sumanta Mukherjee, Nupur Aggarwal, Kanthi Sarpatwar, Giridhar Ganapavarapu, Roman Vaculin
High Explainability Time Series Forecasting Black Box Robust Model Interpretable Feature Model Agnostic Explainability

March 20, 2023

Late Meta-learning Fusion Using Representation Learning for Time Series Forecasting
Terence L. van Zyl
Time Series Forecasting Meta Training Model Fusion Meta Representation E RNN

March 18, 2023

Discovering Predictable Latent Factors for Time Series Forecasting
Jingyi Hou, Zhen Dong, Jiayu Zhou, Zhijie Liu
Time Series Time Series Forecasting Latent Factor Predictability Problem Time Series Forecasting Method

March 14, 2023

Sinkhorn-Flow: Predicting Probability Mass Flow in Dynamical Systems Using Optimal Transport
Mukul Bhutani, J. Zico Kolter
Optimal Transport Time Series Forecasting Dynamical System Sinkhorn Algorithm Prediction Method Probability Flow Transport Problem

March 13, 2023

March 10, 2023

TSMixer: An All-MLP Architecture for Time Series Forecasting
Si-An Chen, Chun-Liang Li, Nate Yoder, Sercan O. Arik, Tomas Pfister
Deep Learning Model Time Series Forecasting Architecture Design Deep Learning Based

March 9, 2023

Enhancing Peak Network Traffic Prediction via Time-Series Decomposition
Tucker Stewart, Bin Yu, Anderson Nascimento, Juhua Hu
Time Series Forecasting Traffic Prediction Microbial Decomposition Network Traffic Theoretical Peak Performance Analysis Volume Prediction

February 28, 2023

Your time series is worth a binary image: machine vision assisted deep framework for time series forecasting
Luoxiao Yang, Xinqi Fan, Zijun Zhang
Computer Vision Time Series Time Series Forecasting Deep Vision Model Deep Framework Binary Image

February 27, 2023

Combating Uncertainties in Wind and Distributed PV Energy Sources Using Integrated Reinforcement Learning and Time-Series Forecasting
Arman Ghasemi, Amin Shojaeighadikolaei, Morteza Hashemi
Reinforcement Learning Time Series Forecasting Smart Grid Energy Management DC Microgrid Application Renewable Generation Wind Pressure Tackle Uncertainty

February 22, 2023

February 20, 2023

Online Evolutionary Neural Architecture Search for Multivariate Non-Stationary Time Series Forecasting
Zimeng Lyu, Alexander Ororbia, Travis Desell
Recurrent Neural Network Neural Architecture Search Time Series Forecasting

February 18, 2023

FrAug: Frequency Domain Augmentation for Time Series Forecasting
Muxi Chen, Zhijian Xu, Ailing Zeng, Qiang Xu
Fine Grained Data Augmentation Time Series Time Series Forecasting

Time Series Forecasting

Papers

Financial Time Series Forecasting using CNN and Transformer

Two Steps Forward and One Behind: Rethinking Time Series Forecasting with Deep Learning

Ensemble Modeling for Time Series Forecasting: an Adaptive Robust Optimization Approach

OFTER: An Online Pipeline for Time Series Forecasting

SimTS: Rethinking Contrastive Representation Learning for Time Series Forecasting

Towards Diverse and Coherent Augmentation for Time-Series Forecasting

TsSHAP: Robust model agnostic feature-based explainability for time series forecasting

Late Meta-learning Fusion Using Representation Learning for Time Series Forecasting

Discovering Predictable Latent Factors for Time Series Forecasting

Sinkhorn-Flow: Predicting Probability Mass Flow in Dynamical Systems Using Optimal Transport

Comparing statistical and machine learning methods for time series forecasting in data-driven logistics -- A simulation study

Hybrid Variational Autoencoder for Time Series Forecasting

TSMixer: An All-MLP Architecture for Time Series Forecasting

Enhancing Peak Network Traffic Prediction via Time-Series Decomposition

Your time series is worth a binary image: machine vision assisted deep framework for time series forecasting

Combating Uncertainties in Wind and Distributed PV Energy Sources Using Integrated Reinforcement Learning and Time-Series Forecasting

The DeepCAR Method: Forecasting Time-Series Data That Have Change Points

Dish-TS: A General Paradigm for Alleviating Distribution Shift in Time Series Forecasting

Online Evolutionary Neural Architecture Search for Multivariate Non-Stationary Time Series Forecasting

FrAug: Frequency Domain Augmentation for Time Series Forecasting