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

November 18, 2024

A Hybrid Loss Framework for Decomposition-based Time Series Forecasting Methods: Balancing Global and Component Errors
Ronghui Han, Duanyu Feng, Hongyu Du, Hao Wang
Loss Function NCD Method Time Series Forecasting World Event Connected Component Hybrid Loss Time Series Forecasting Method Seasonal Trend Decomposition Time Series Decomposition

November 16, 2024

FlowScope: Enhancing Decision Making by Time Series Forecasting based on Prediction Optimization using HybridFlow Forecast Framework
Nitin Sagar Boyeena, Begari Susheel Kumar
Time Series Forecasting Decision Making LSTM Network Hybrid Deep Learning Integrated Moving Average Forecast Combination

November 15, 2024

November 12, 2024

Retrieval Augmented Time Series Forecasting
Kutay Tire, Ege Onur Taga, Muhammed Emrullah Ildiz, Samet Oymak
Zero Shot Retrieval Augmented Generation Time Series Forecasting Retrieval Augmented Time Series Foundation Model

November 11, 2024

Multi-Modal Forecaster: Jointly Predicting Time Series and Textual Data
Kai Kim, Howard Tsai, Rajat Sen, Abhimanyu Das, Zihao Zhou, Abhishek Tanpure, Mathew Luo, Rose Yu
Time Series Time Series Forecasting Multimodal Dataset Multimodal Benchmark Datasets

November 6, 2024

Fully Automated Correlated Time Series Forecasting in Minutes
Xinle Wu, Xingjian Wu, Dalin Zhang, Miao Zhang, Chenjuan Guo, Bin Yang, Christian S. Jensen
Time Series Forecasting State of the Art Forecasting Forecasting Model Meeting Minute Forecasting Task Correlated Time Series Forecasting

November 5, 2024

A Mamba Foundation Model for Time Series Forecasting
Haoyu Ma, Yushu Chen, Wenlai Zhao, Jinzhe Yang, Yingsheng Ji, Xinghua Xu, Xiaozhu Liu, Hao Jing, Shengzhuo Liu, Guangwen Yang
Time Series Forecasting Time Series Foundation Model Mamba Based Model Mamba Based Encoder Decoder

November 3, 2024

October 31, 2024

LSEAttention is All You Need for Time Series Forecasting
Dizhen Liang
Transformer Model Time Series Forecasting Multivariate Time Series Multivariate Time Series Forecasting Transformer Based Architecture

October 30, 2024

October 29, 2024

A Systematic Literature Review of Spatio-Temporal Graph Neural Network Models for Time Series Forecasting and Classification
Flavio Corradini, Marco Gori, Carlo Lucheroni, Marco Piangerelli, Martina Zannotti
Graph Neural Network Full Model Classification Code Time Series Forecasting Spatio Temporal Time Series Classification Systematic Literature Review Temporal Graph Neural Network

October 28, 2024

A Temporal Linear Network for Time Series Forecasting
Remi Genet, Hugo Inzirillo
Time Series Forecasting Temporal Information Temporal Network Temporal Neural Network

October 27, 2024

October 25, 2024

Enhancing Battery Storage Energy Arbitrage with Deep Reinforcement Learning and Time-Series Forecasting
Manuel Sage, Joshua Campbell, Yaoyao Fiona Zhao
Deep Learning LeArning Abstract Deep Reinforcement Learning Time Series Forecasting Deep Q Network Deep Reinforcement Energy Storage Electricity Price Energy Arbitrage

October 24, 2024

Time Series Forecasting

Papers

A Hybrid Loss Framework for Decomposition-based Time Series Forecasting Methods: Balancing Global and Component Errors

FlowScope: Enhancing Decision Making by Time Series Forecasting based on Prediction Optimization using HybridFlow Forecast Framework

FengWu-W2S: A deep learning model for seamless weather-to-subseasonal forecast of global atmosphere

Is Precise Recovery Necessary? A Task-Oriented Imputation Approach for Time Series Forecasting on Variable Subset

Retrieval Augmented Time Series Forecasting

Multi-Modal Forecaster: Jointly Predicting Time Series and Textual Data

Fully Automated Correlated Time Series Forecasting in Minutes

A Mamba Foundation Model for Time Series Forecasting

FilterNet: Harnessing Frequency Filters for Time Series Forecasting

PSformer: Parameter-efficient Transformer with Segment Attention for Time Series Forecasting

LSEAttention is All You Need for Time Series Forecasting

Sequential Order-Robust Mamba for Time Series Forecasting

DisenTS: Disentangled Channel Evolving Pattern Modeling for Multivariate Time Series Forecasting

A Systematic Literature Review of Spatio-Temporal Graph Neural Network Models for Time Series Forecasting and Classification

A Temporal Linear Network for Time Series Forecasting

TEAFormers: TEnsor-Augmented Transformers for Multi-Dimensional Time Series Forecasting

Deconfounding Time Series Forecasting

Enhancing Battery Storage Energy Arbitrage with Deep Reinforcement Learning and Time-Series Forecasting

Context is Key: A Benchmark for Forecasting with Essential Textual Information

Retrieval-Augmented Diffusion Models for Time Series Forecasting