facebookincubator/prophet
Prophet
Prophet is a predictive analytics framework and time series regression library designed for forecasting future values. It uses additive models to fit non-linear growth and periodic seasonal patterns, providing tools for producing forecasts with integrated error measurement.
The project handles multiple seasonalities and holiday effects to improve accuracy for periodic data. It supports the integration of external regressors and manages data irregularities, such as missing data and outliers, to maintain prediction stability.
The framework covers a broad range of analysis capabilities, including predictive trend modeling and business cycle analysis. It includes tools for demand planning workflows and historical cross-validation to evaluate forecast accuracy through quantitative error metrics.
Features
- Forecasting - Provides a comprehensive framework for predicting future values based on historical time-series patterns.
- Piecewise Linear Trends - Models growth using a series of linear segments with changepoints to handle abrupt shifts in trend direction.
- Predictive Machine Learning Analytics - Provides an integrated statistical framework for forecasting trends and recognizing patterns in time series data.
- Forecast Accuracy Validation - Evaluates the precision of predictions using historical cross-validation and quantitative error metric analysis.
- Predictive Trend Modeling - Analyzes long-term growth patterns and adjusts for sudden shifts or outliers in historical datasets.
- Cross Validation Evaluation - Evaluates predictive performance using historical data and generates error metrics to measure accuracy.
- Probabilistic Programming - Integrates the Stan probabilistic programming language for Bayesian inference and posterior sampling of parameters.
- Time Series Forecasting - Offers a tool for predicting future values in temporal data using additive models.
- Seasonal Pattern Modeling - Incorporates additive and multiplicative seasonal effects and holiday markers to improve forecasting accuracy.
- Time Series Modeling - Functions as a library for fitting trends to time series data while integrating external regressors.
- Time Series Decomposition - Implements additive decomposition to separate time series data into seasonal, trend, and holiday components.
- Fourier-Series Seasonality - Uses Fourier series to approximate daily, weekly, and yearly periodic patterns in time series data.
- Maximum A Posteriori Estimators - Fits model parameters using maximum a posteriori estimation to incorporate prior distributions with observed data.
- Irregular Time Series - Maintains prediction stability by managing missing data and outliers in irregular time series.
- Business Cycle Analysis - Identifies periodic growth and seasonal fluctuations in organizational data to plan for future resource needs.
- Demand Planning - Estimates future product or service demand while accounting for holidays and external market influences.
- External Regressors - Supports adding external regressors to capture additional influences on the observed time series trend.
- AI and Forecasting - Tool for forecasting time series with multiple seasonalities.
- Machine Learning - Forecasting tool for time series with multiple seasonalities.
Star history
How this analysis was created: This summary and feature list are AI-generated from collected project material and can contain mistakes. Stars, license and language are imported from GitHub. Inclusion does not mean that we have tested or audited this project. Check the source documentation for any feature you depend on. Learn more on our About page.
