Summary of Explainable Adaptive Tree-based Model Selection For Time Series Forecasting, by Matthias Jakobs and Amal Saadallah
Explainable Adaptive Tree-based Model Selection for Time Series Forecasting
by Matthias Jakobs, Amal Saadallah
First submitted to arxiv on: 2 Jan 2024
Categories
- Main: Machine Learning (cs.LG)
- Secondary: Artificial Intelligence (cs.AI)
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary The proposed novel method for online selection of tree-based models using TreeSHAP explainability method in time series forecasting addresses the overfitting problem and improves interpretability. The approach starts with an arbitrary set of tree-based models, ranks them based on performance, and selects the best model adaptively following drift detection in the time series. This framework supports explainability on three levels: online input importance, model selection, and model output explanation. Experimental results on real-world datasets demonstrate excellent or comparable performance to state-of-the-art approaches and baselines. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This paper proposes a new way to choose the best tree-based models for predicting future values in time series data. The method starts with many different models, then picks the best one based on how well it does. It also explains why each model is chosen and what’s important about the input data. This helps with making decisions that are fair and easy to understand. The results show that this method performs just as well as other approaches. |
Keywords
* Artificial intelligence * Overfitting * Time series
