From black box to clear box: A hypothesis testing framework for scalar regression problems using deep artificial neural networks

Messner, Wolfgang

doi:10.1016/j.asoc.2023.110729

Cited by 7 publications

(1 citation statement)

References 53 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Example applications include designing regulatorily compliant, fair [16], transparent, and trustworthy prediction models [17]. Another area of IML focuses on the interpretation of the effects of covariates on prediction [18][19][20]. Here, the focus is on global model interpretability, which means that the prediction function over the whole covariate distribution is the focus of interest instead of explaining single local predictions for specific covariate values [21].…”

Section: Introductionmentioning

confidence: 99%

Interaction Difference Hypothesis Test for Prediction Models

Welchowski,

Edelmann

2024

MAKE

View full text Add to dashboard Cite

Machine learning research focuses on the improvement of prediction performance. Progress was made with black-box models that flexibly adapt to the given data. However, due to their increased complexity, black-box models are more difficult to interpret. To address this issue, techniques for interpretable machine learning have been developed, yet there is still a lack of methods to reliably identify interaction effects between predictors under uncertainty. In this work, we present a model-agnostic hypothesis test for the identification of interaction effects in black-box machine learning models. The test statistic is based on the difference between the variance of the estimated prediction function and a version of the estimated prediction function without interaction effects derived via partial dependence functions. The properties of the proposed hypothesis test were explored in simulations of linear and nonlinear models. The proposed hypothesis test can be applied to any black-box prediction model, and the null hypothesis of the test can be flexibly specified according to the research question of interest. Furthermore, the test is computationally fast to apply, as the null distribution does not require the resampling or refitting of black-box prediction models.

show abstract