A novel approach to explain the black-box nature of machine learning in compressive strength predictions of concrete using Shapley additive explanations (SHAP)

Machine learning (ML) techniques are often employed for the accurate prediction of the compressive strength of concrete. Despite higher accuracy, previous ML models failed to interpret the rationale behind predictions. Model interpretability is essential to appeal to the interest of domain experts. Therefore, overcoming research gaps identified, this research study proposes a way to predict the compressive strength of concrete using supervised ML algorithms (Decision tree, Extra tree, Adaptive boost (AdaBoost), Extreme gradient boost (XGBoost), Light gradient boosting method (LGBM), and Laplacian Kernel Ridge Regression (LKRR). Alternatively, SHapley Additive exPlainations (SHAP) - a novel black-box interpretation approach - was employed to elucidate the predictions. The comparison revealed that tree-based algorithms and LKRR provide acceptable accuracy for compressive strength predictions. Moreover, XGBoost and LKRR algorithms evinced superior performance (R = 0.98). According to SHAP interpretation, XGBoost predictions capture complex relationships among the constituents. On the other hand, SHAP provides unified measures on feature importance and the impact of a variable for a prediction. Interestingly, SHAP interpretations were in accordance with what is generally observed in the compressive behavior of concrete, thus validating the causality of ML predictions.

Automated summary

This research uses machine learning algorithms to predict the compressive strength of concrete and employs a black-box interpretation method called SHAP to explain the predictions. The results show that tree-based algorithms and LKRR have good accuracy in predicting compressive strength, with XGBoost and LKRR performing exceptionally well.