Prophet

What Prophet is

Prophet is a forecasting procedure for time-series data that models non-linear trends, yearly, weekly, and daily seasonality, and holiday effects. The project says it works best with strong seasonal effects and several seasons of historical data. It describes Prophet as robust to missing data and trend shifts, and says it typically handles outliers well. Users can adjust forecasts with human-interpretable parameters and add domain knowledge. Prophet has R and Python implementations that share Stan code for fitting. Its documentation covers country holidays, custom seasonalities, additional regressors, uncertainty intervals, and cross-validation. R installation is documented through CRAN, while Python installation is through PyPI or conda-forge. The open-source software is under the MIT License, and the Prophet plan is free. Python requires version 3.7 or later; the installation guide specifies at least 4 GB of VM memory to install and 2 GB to use it. Windows setup has compiler requirements: R installation needs Rtools, while Python installation with cmdstanpy needs a Unix-compatible C compiler. As of v1.4.0, the project is in maintenance mode, accepting bug fixes, dependency updates, and R parity changes, with no new features planned.