arXiv (Cornell University) · 2023 · 42 citations · 0 references
ComputingComputer ScienceForecastingMachine LearningNatural Language ProcessingLanguage ModelingLanguage ModelsTime Series ForecastingTime Series ModelingTime Series PredictionDecoder DesignDeep Learning For Time Series ForecastingLarge Language ModelsTime Series Representation Learning
Motivated by recent advances in large language models for Natural Language Processing (NLP), we design a time-series foundation model for forecasting whose out-of-the-box zero-shot performance on a variety of public datasets comes close to the accuracy of state-of-the-art supervised forecasting models for each individual dataset. Our model is based on pretraining a patched-decoder style attention model on a large time-series corpus, and can work well across different forecasting history lengths, prediction lengths and temporal granularities.