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

July 25, 2024

DAM: Towards A Foundation Model for Time Series Forecasting
Luke Darlow, Qiwen Deng, Ahmed Hassan, Martin Asenov, Rajkarn Singh, Artjom Joosen, Adam Barker, Amos Storkey
Foundation Model Time Series Forecasting Multivariate Time Series Forecasting Long Term Forecasting Time Series Datasets

July 24, 2024

Channel-Aware Low-Rank Adaptation in Time Series Forecasting
Tong Nie, Yuewen Mei, Guoyang Qin, Jian Sun, Wei Ma
Time Series Forecasting Adaptation Concern Long Term Time Series Forecasting Channel Wise Cross Channel

July 23, 2024

Can time series forecasting be automated? A benchmark and analysis
Anvitha Thirthapura Sreedhara, Joaquin Vanschoren
New Benchmark General Analysis Time Series Forecasting Forecasting Method Time Series Forecasting Method

July 21, 2024

Deep State Space Recurrent Neural Networks for Time Series Forecasting
Hugo Inzirillo
Recurrent Neural Network Long Short Term Memory Time Series Forecasting Kolmogorov Arnold Network Deep State Space

July 20, 2024

FMamba: Mamba based on Fast-attention for Multivariate Time-series Forecasting
Shusen Ma, Yu Kang, Peng Bai, Yun-Bo Zhao
Time Series Forecasting Attention Module Mamba in Mamba Temporal Correlation Attention Operation

July 18, 2024

Revisiting Attention for Multivariate Time Series Forecasting
Haixiang Wu
Attention Mechanism Human Attention Time Series Forecasting Multivariate Time Series Forecasting Convolution Head Orthogonal Attention

July 17, 2024

Not All Frequencies Are Created Equal:Towards a Dynamic Fusion of Frequencies in Time-Series Forecasting
Xingyu Zhang, Siyu Zhao, Zeen Song, Huijie Guo, Jianqi Zhang, Changwen Zheng, Wenwen Qiang
Time Series Forecasting Long Term Time Series Forecasting Long Term Forecasting Dominant Low Frequency Time Series Forecasting Method Dynamic Fusion

July 10, 2024

July 6, 2024

Integer-only Quantized Transformers for Embedded FPGA-based Time-series Forecasting in AIoT
Tianheng Ling, Chao Qian, Gregor Schiele
Transformer Model Time Series Forecasting Hardware Accelerator Embedded System Device Inference Integer Quantization Quantized Transformer

July 3, 2024

Multiple-Resolution Tokenization for Time Series Forecasting with an Application to Pricing
Egon Peršak, Miguel F. Anjos, Sebastian Lautz, Aleksandar Kolev
Application Proficiency Time Series Transformer Architecture Time Series Forecasting Deep Learning Architecture Curious Price

July 2, 2024

July 1, 2024

June 29, 2024

Addressing Prediction Delays in Time Series Forecasting: A Continuous GRU Approach with Derivative Regularization
Sheo Yon Jhin, Seojin Kim, Noseong Park
Time Series Forecasting Gated Recurrent Unit Gradient Regularization Temporal Regularization Delay Prediction

June 24, 2024

Forecasting with Deep Learning: Beyond Average of Average of Average Performance
Vitor Cerqueira, Luis Roque, Carlos Soares
Deep Learning Time Series Forecasting State of the Art Forecasting Multi Step Forecasting Model Univariate Time Series Forecasting Average Performance

June 22, 2024

Are Language Models Actually Useful for Time Series Forecasting?
Mingtian Tan, Mike A. Merrill, Vinayak Gupta, Tim Althoff, Thomas Hartvigsen
Large Language Model Language Model Time Series Forecasting LLM Based

June 20, 2024

Time Series Forecasting

Papers

DAM: Towards A Foundation Model for Time Series Forecasting

Channel-Aware Low-Rank Adaptation in Time Series Forecasting

Can time series forecasting be automated? A benchmark and analysis

Deep State Space Recurrent Neural Networks for Time Series Forecasting

FMamba: Mamba based on Fast-attention for Multivariate Time-series Forecasting

Revisiting Attention for Multivariate Time Series Forecasting

Not All Frequencies Are Created Equal:Towards a Dynamic Fusion of Frequencies in Time-Series Forecasting

Toto: Time Series Optimized Transformer for Observability

ViTime: A Visual Intelligence-Based Foundation Model for Time Series Forecasting

Integer-only Quantized Transformers for Embedded FPGA-based Time-series Forecasting in AIoT

Multiple-Resolution Tokenization for Time Series Forecasting with an Application to Pricing

Large Scale Hierarchical Industrial Demand Time-Series Forecasting incorporating Sparsity

Learning Graph Structures and Uncertainty for Accurate and Calibrated Time-series Forecasting

MARLP: Time-series Forecasting Control for Agricultural Managed Aquifer Recharge

Macroeconomic Forecasting with Large Language Models

Addressing Prediction Delays in Time Series Forecasting: A Continuous GRU Approach with Derivative Regularization

Forecasting with Deep Learning: Beyond Average of Average of Average Performance

Are Language Models Actually Useful for Time Series Forecasting?

aeon: a Python toolkit for learning from time series

Understanding Different Design Choices in Training Large Time Series Models