Forecasting Benchmark

Forecasting benchmark research aims to establish standardized datasets and evaluation metrics for assessing the accuracy and efficiency of time series forecasting models. Current efforts focus on developing larger, more diverse datasets encompassing various data modalities (including metadata) and addressing challenges like long-term dependencies and distributional shifts, often employing transformer architectures, convolutional neural networks (CNNs), and multi-layer perceptrons (MLPs) with innovative techniques like coarsening and random projections. These advancements are crucial for improving the reliability and generalizability of forecasting models across diverse real-world applications, from weather prediction and financial analysis to energy planning and market trading.

Papers

November 3, 2024

FilterNet: Harnessing Frequency Filters for Time Series Forecasting
Kun Yi, Jingru Fei, Qi Zhang, Hui He, Shufeng Hao, Defu Lian, Wei Fan
Time Series Time Series Forecasting Learnable Filter Frequency Learning Forecasting Benchmark

October 31, 2024

In-Context Fine-Tuning for Time-Series Foundation Models
Abhimanyu Das, Matthew Faw, Rajat Sen, Yichen Zhou
Zero Shot Fine Tuning Time Series Time Series Foundation Model Forecasting Benchmark

October 4, 2024

Metadata Matters for Time Series: Informative Forecasting with Transformers
Jiaxiang Dong, Haixu Wu, Yuxuan Wang, Li Zhang, Jianmin Wang, Mingsheng Long
Transformer Megatron Decepticons Time Series Metadata Information Time Series Transformer Interpretable Forecast Forecasting Benchmark

June 20, 2024

How far are today's time-series models from real-world weather forecasting applications?
Tao Han, Song Guo, Zhenghao Chen, Wanghan Xu, Lei Bai
Weather Data Forecasting Benchmark Continuous Weather

May 9, 2024

Multi-Scale Dilated Convolution Network for Long-Term Time Series Forecasting
Feifei Li, Suhan Guo, Feng Han, Jian Zhao, Furao Shen
Time Series Autoregressive Model Long Term Time Series Forecasting Dilated Convolutional Neural Network Forecasting Benchmark

May 6, 2024

Boosting MLPs with a Coarsening Strategy for Long-Term Time Series Forecasting
Nannan Bian, Minhong Zhu, Li Chen, Weiran Cai
Multi Layer Long Term Time Series Forecasting Multi Layer Perceptron accuratE Prediction Graph Coarsening Forecasting Benchmark

February 29, 2024

TimeXer: Empowering Transformers for Time Series Forecasting with Exogenous Variables
Yuxuan Wang, Haixu Wu, Jiaxiang Dong, Guo Qin, Haoran Zhang, Yong Liu, Yunzhong Qiu, Jianmin Wang, Mingsheng Long
Transformer Megatron Decepticons Time Series Forecasting Exogenous Variable Global Endogenous Variate Forecasting Benchmark Exogenous Information

February 16, 2024

RPMixer: Shaking Up Time Series Forecasting with Random Projections for Large Spatial-Temporal Data
Chin-Chia Michael Yeh, Yujie Fan, Xin Dai, Uday Singh Saini, Vivian Lai, Prince Osei Aboagye, Junpeng Wang, Huiyuan Chen, Yan Zheng, Zhongfang Zhuang, Liang Wang, Wei Zhang
Time Series Forecasting Random Projection Spatio Temporal Forecasting General Time Series Large Scale Spatio Temporal Forecasting Benchmark Forecasting Architecture

February 14, 2024

Loss Shaping Constraints for Long-Term Time Series Forecasting
Ignacio Hounie, Javier Porras-Valenzuela, Alejandro Ribeiro
Time Series Forecasting Long Term Time Series Forecasting Forecasting Benchmark Constraint Loss

December 22, 2023

C2FAR: Coarse-to-Fine Autoregressive Networks for Precise Probabilistic Forecasting
Shane Bergsma, Timothy Zeyl, Javad Rahimipour Anaraki, Lei Guo
Recurrent Neural Network Probabilistic Forecast Forecasting Benchmark

October 1, 2023

PatchMixer: A Patch-Mixing Architecture for Long-Term Time Series Forecasting
Zeying Gong, Yujin Tang, Junwei Liang
Neural Network Architecture Design Long Term Time Series Forecasting Forecasting Benchmark Prediction Head

September 27, 2023

Unified Long-Term Time-Series Forecasting Benchmark
Jacek Cyranka, Szymon Haponiuk
LSTM Network Time Series Data Long Term Time Series Forecasting Long Term Forecasting Forecasting Benchmark

March 31, 2023

Simple 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

November 17, 2022

DSLOB: A Synthetic Limit Order Book Dataset for Benchmarking Forecasting Algorithms under Distributional Shift
Defu Cao, Yousef El-Laham, Loc Trinh, Svitlana Vyetrenko, Yan Liu
Distribution Shift Distribution Data Available Datasets Multi Agent Market Limit Order Book Forecasting Benchmark Distribution Shift Benchmark