Table of Contents¶
Welcome to the skforecast user guides! This comprehensive collection of guides is designed to help you navigate through the various features and functionalities of skforecast. Whether you are a beginner or an advanced user, you will find the necessary resources to master time series forecasting with skforecast. Below, you will find the user guides categorized by topic for easier navigation.
Single series Forecasters
- Recursive multi-step forecasting
- Direct multi-step forecasting
- ARIMA and SARIMAX forecasting
- Foreasting baseline
Global Forecasters (multiple series)
- Independent multi-time series forecasting
- Series with different lengths and different exogenous variables
- Dependent multivariate series forecasting
- Deep learning Recurrent Neural Networks
Feature Engineering
- Exogenous variables
- Window and custom features
- Categorical features
- Calendars features
- Data transformations
- Differentiation
- Feature selection
Model Evaluation and Tuning
Probabilistic Forecasting
Model Explainability
Model deployment
Plotting
Datasets
Additional Resources
- Skforecast 0.14 Migration guide
- Weighted time series forecasting
- Stacking multiple models
- Forecasting with XGBoost and LightGBM
- Skforecast in GPU
FAQ and forecasting tips
- Avoid negative predictions when forecasting
- Forecasting time series with missing values
- Forecasting with delayed historical data
- Backtesting vs One-step-ahead
- Cyclical features in time series
- Time series aggregation
- Parallelization in skforecast
- Profiling skforecast
We hope you find these guides helpful. If you have any questions or need further assistance, please don't hesitate to reach out to the skforecast community. Remember to visit the FAQ and forecasting tips page for answers to frequently asked questions and forecasting tips.