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

October 3, 2023

Perceiver-based CDF Modeling for Time Series Forecasting
Cat P. Le, Chris Cannella, Ali Hasan, Yuting Ng, Vahid Tarokh
Time Series Forecasting Multimodal Data Cumulative Distribution Function Perception Data Perceiver IO

October 2, 2023

Modality-aware Transformer for Financial Time series Forecasting
Hajar Emami, Xuan-Hong Dang, Yousaf Shah, Petros Zerfos
Time Series Forecasting Multimodal Transformer Financial Time Series Data Modality Modality Aware Transformer

September 26, 2023

Balancing Computational Efficiency and Forecast Error in Machine Learning-based Time-Series Forecasting: Insights from Live Experiments on Meteorological Nowcasting
Elin Törnquist, Wagner Costa Santos, Timothy Pogue, Nicholas Wingle, Robert A. Caulk
Time Series Forecasting Numerical Weather Prediction Trade Offs Physic Experiment Short Term Forecasting Forecast Error Convection Nowcasting

September 23, 2023

September 18, 2023

Graph-enabled Reinforcement Learning for Time Series Forecasting with Adaptive Intelligence
Thanveer Shaik, Xiaohui Tao, Haoran Xie, Lin Li, Jianming Yong, Yuefeng Li
Reinforcement Learning Time Series Forecasting Traditional RNNs Graph Reinforcement Learning Adaptive AI Graphical Neural Network

September 5, 2023

Encoding Seasonal Climate Predictions for Demand Forecasting with Modular Neural Network
Smit Marvaniya, Jitendra Singh, Nicolas Galichet, Fred Ochieng Otieno, Geeth De Mel, Kommy Weldemariam
Time Series Forecasting Demand Forecasting Modular Neural Network Seasonal Climate

August 24, 2023

Business Metric-Aware Forecasting for Inventory Management
Helen Zhou, Sercan O. Arik, Jingtao Wang
Time Series Forecasting Inventory Management Univariate Time Series Forecasting Downstream Performance

August 16, 2023

LLM4TS: Aligning Pre-Trained LLMs as Data-Efficient Time-Series Forecasters
Ching Chang, Wei-Yao Wang, Wen-Chih Peng, Tien-Fu Chen
Large Language Model Fine Tuning Multi Scale Time Series Forecasting Pre Trained Large Language Model Downstream Forecasting Task Efficient Time Series Forecasting

August 10, 2023

A Forecaster's Review of Judea Pearl's Causality: Models, Reasoning and Inference, Second Edition, 2009
Feng Li
Complex Reasoning Scientific Inference Causal Inference Time Series Forecasting Causal Effect Causal Pattern

July 28, 2023

July 27, 2023

TimeGNN: Temporal Dynamic Graph Learning for Time Series Forecasting
Nancy Xu, Chrysoula Kosma, Michalis Vazirgiannis
Time Series Forecasting Multivariate Time Series Temporal Graph Temporal Graph Learning

July 19, 2023

TimeTuner: Diagnosing Time Representations for Time-Series Forecasting with Counterfactual Explanations
Jianing Hao, Qing Shi, Yilin Ye, Wei Zeng
Deep Learning Time Series Forecasting Counterfactual Explanation Model Prediction Time Series Representation Temporal Representation

July 13, 2023

MPR-Net:Multi-Scale Pattern Reproduction Guided Universality Time Series Interpretable Forecasting
Tianlong Zhao, Xiang Ma, Xuemei Li, Caiming Zhang
Time Series Forecasting Future Trend Multiscale System

July 6, 2023

FITS: Modeling Time Series with $10k$ Parameters
Zhijian Xu, Ailing Zeng, Qiang Xu
Time Series Time Series Forecasting Time Series Data Many Parameter Time Series Analysis Better FiT

July 5, 2023

Multimodal Temporal Fusion Transformers Are Good Product Demand Forecasters
Maarten Sukel, Stevan Rudinac, Marcel Worring
Time Series Forecasting Multimodal Information Demand Forecasting Multimodal Processing Temporal Fusion Transformer

July 4, 2023

Unlocking the Potential of Deep Learning in Peak-Hour Series Forecasting
Zhenwei Zhang, Xin Wang, Jingyuan Xie, Heling Zhang, Yuantao Gu
Deep Learning Time Series Forecasting Full Potential State of the Art Deep Time Series Forecasting Model

July 3, 2023

Exploring the Multi-modal Demand Dynamics During Transport System Disruptions
Ali Shateri Benam, Angelo Furno, Nour-Eddin El Faouzi
Time Series Forecasting Disruptive Event Urban Mobility Disruption Prediction

June 30, 2023

Improving the Transferability of Time Series Forecasting with Decomposition Adaptation
Yan Gao, Yan Wang, Qiang Wang
Time Series Forecasting Task Transferability Multivariate Time Series Forecasting Joint Distribution Adaptation Neural Forecasting Decomposition Network

Time Series Forecasting

Papers

Perceiver-based CDF Modeling for Time Series Forecasting

Modality-aware Transformer for Financial Time series Forecasting

Balancing Computational Efficiency and Forecast Error in Machine Learning-based Time-Series Forecasting: Insights from Live Experiments on Meteorological Nowcasting

Enhancing Prediction and Analysis of UK Road Traffic Accident Severity Using AI: Integration of Machine Learning, Econometric Techniques, and Time Series Forecasting in Public Health Research

Monotonic Neural Ordinary Differential Equation: Time-series Forecasting for Cumulative Data

Graph-enabled Reinforcement Learning for Time Series Forecasting with Adaptive Intelligence

Encoding Seasonal Climate Predictions for Demand Forecasting with Modular Neural Network

Business Metric-Aware Forecasting for Inventory Management

LLM4TS: Aligning Pre-Trained LLMs as Data-Efficient Time-Series Forecasters

A Forecaster's Review of Judea Pearl's Causality: Models, Reasoning and Inference, Second Edition, 2009

DeepTSF: Codeless machine learning operations for time series forecasting

A Distance Correlation-Based Approach to Characterize the Effectiveness of Recurrent Neural Networks for Time Series Forecasting

TimeGNN: Temporal Dynamic Graph Learning for Time Series Forecasting

TimeTuner: Diagnosing Time Representations for Time-Series Forecasting with Counterfactual Explanations

MPR-Net:Multi-Scale Pattern Reproduction Guided Universality Time Series Interpretable Forecasting

FITS: Modeling Time Series with $10k$ Parameters

Multimodal Temporal Fusion Transformers Are Good Product Demand Forecasters

Unlocking the Potential of Deep Learning in Peak-Hour Series Forecasting

Exploring the Multi-modal Demand Dynamics During Transport System Disruptions

Improving the Transferability of Time Series Forecasting with Decomposition Adaptation