Open Internet by MindsNet

google-research/timesfm

TimesFM (Time Series Foundation Model) is a pretrained time-series foundation model developed by Google Research for accurate and efficient time-series forecasting. It offers a range of features, including support for long context lengths and quantile forecasting. This model is designed to be a versatile tool for various time-series forecasting tasks. Best for: Data scientists, analysts, and developers working with time-series data Use cases: Predicting stock prices or financial market trends; Forecasting weather patterns or climate changes; Analyzing and predicting customer demand or sales trends Highlights: High-performance forecasting with up to 16k context length support; Continuous quantile forecast up to 1k horizon; Lightweight with 200M parameters, offering efficiency and accuracy

Computing & Technology, Computer Science, Software Engineering