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
Lag-Llama: Towards Foundation Models for Probabilistic Time Series Forecasting
Kashif Rasul, Arjun Ashok, Andrew Robert Williams, Hena Ghonia, Rishika Bhagwatkar, Arian Khorasani, Mohammad Javad Darvishi Bayazi, George Adamopoulos, Roland Riachi, Nadhir Hassen, Marin Biloš, Sahil Garg, Anderson Schneider, Nicolas Chapados, Alexandre Drouin, Valentina Zantedeschi, Yuriy Nevmyvaka, Irina Rish
Counterfactual Explanations for Time Series Forecasting
Zhendong Wang, Ioanna Miliou, Isak Samsten, Panagiotis Papapetrou
Pushing the Limits of Pre-training for Time Series Forecasting in the CloudOps Domain
Gerald Woo, Chenghao Liu, Akshat Kumar, Doyen Sahoo
TEMPO: Prompt-based Generative Pre-trained Transformer for Time Series Forecasting
Defu Cao, Furong Jia, Sercan O Arik, Tomas Pfister, Yixiang Zheng, Wen Ye, Yan Liu