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

We present a model-agnostic framework for jointly optimizing the predictiveperformance and interpretability of supervised machine learning models fortabular data. Interpretability is quantified via three measures: featuresparsity, interaction sparsity of features, and sparsity of non-monotonefeature effects. By treating hyperparameter optimization of a machine learningalgorithm as a multi-objective optimization problem, our framework allows forgenerating diverse models that trade off high performance and ease ofinterpretability in a single optimization run. Efficient optimization isachieved via augmentation of the search space of the learning algorithm byincorporating feature selection, interaction and monotonicity constraints intothe hyperparameter search space. We demonstrate that the optimization problemeffectively translates to finding the Pareto optimal set of groups of selectedfeatures that are allowed to interact in a model, along with finding theiroptimal monotonicity constraints and optimal hyperparameters of the learningalgorithm itself. We then introduce a novel evolutionary algorithm that canoperate efficiently on this augmented search space. In benchmark experiments,we show that our framework is capable of finding diverse models that are highlycompetitive or outperform state-of-the-art XGBoost or Explainable BoostingMachine models, both with respect to performance and interpretability.

Multi-Objective Optimization of Performance and Interpretability of Tabular Supervised Machine Learning Models