English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Low-order functional ANOVA (fANOVA) models have been rediscovered in themachine learning (ML) community under the guise of inherently interpretablemachine learning. Explainable Boosting Machines or EBM (Lou et al. 2013) andGAMI-Net (Yang et al. 2021) are two recently proposed ML algorithms for fittingfunctional main effects and second-order interactions. We propose a newalgorithm, called GAMI-Tree, that is similar to EBM, but has a number offeatures that lead to better performance. It uses model-based trees as baselearners and incorporates a new interaction filtering method that is better atcapturing the underlying interactions. In addition, our iterative trainingmethod converges to a model with better predictive performance, and theembedded purification ensures that interactions are hierarchically orthogonalto main effects. The algorithm does not need extensive tuning, and ourimplementation is fast and efficient. We use simulated and real datasets tocompare the performance and interpretability of GAMI-Tree with EBM andGAMI-Net.

Using Model-Based Trees with Boosting to Fit Low-Order Functional ANOVA Models