Chapter 8 · Part 4
Advanced Machine Learning for Forecasting
Where ML beats classical methods and where it doesn't. Limitations of classical methods, advanced feature engineering, trend and seasonality detection, clustering, gradient boosting, hyperparameter strategies, global ML models, and the GBDT failure modes specific to time series.
Learning objectives
By the end of this chapter you will be able to:
- ▸Frame a forecasting problem so a gradient-boosted tree can solve it
- ▸Choose between local and global ML approaches
- ▸Apply clustering to time series forecasting
- ▸Avoid the GBDT failure modes specific to time series
- 1.1Limitations of Classical Methods
- 2.1Advanced Feature Engineering for Time Series
- 3.1Advanced Feature Engineering for Time Series Forecasting: Techniques, Best Practices, and Practical Applications
- 4.1Trend Detection and Modeling in Time Series
- 5.1Seasonality in Time Series: Detection, Testing, and Treatment with Machine Learning Models
- 6.1Clustering in Time Series Forecasting
- 7.1Gradient Boosting for Time Series Forecasting
- 8.1GBDT Limitations and Mitigation Strategies for Time Series Forecasting
- 9.1Hyperparameter Tuning Strategies
- 10.1Global Machine Learning Models
- 11.1Implementation Techniques
- 12.1Robust Evaluation and Validation
- 13.1Failure Modes of Gradient Boosted Decision Trees (GBDTs)
- 14.1Refining GBDT Performance: Strategy, Hybridization, and Limits
Get the full chapter
All eleven chapters · 478 references · private Discord community.
← Previous · Chapter 7
Feature Engineering for Time Series
Next · Chapter 9 →
Deep Learning for Time Series