Application of a Hybrid Explainable ML–MCDM Approach for the Performance Optimisation of Self-Compacting Concrete Containing Crumb Rubber and Calcium Carbide Residue

The combined incorporation of crumb rubber (CR) and calcium carbide residue (CCR) in self-compacting concrete (SCC) induces competing and nonlinear effects on its fresh and hardened properties, making the simultaneous optimisation of workability, strength, durability, and stability challenging. CR reduces density and enhances deformability and flow stability but adversely affects strength, whereas CCR improves particle packing, cohesiveness, and early-age strength up to an optimal replacement level. To systematically address these trade-offs, this study proposes an integrated multi-criteria decision-making (MCDM)–explainable machine learning–global optimisation framework for sustainable SCC mix design. A composite performance score encompassing fresh, mechanical, durability, and thermal indicators is constructed using a weighted MCDM scheme and learned through surrogate machine-learning models. Three learners—glmnet, ranger, and xgboost—are tuned using v-fold cross-validation, with xgboost demonstrating the highest predictive fidelity. Given the limited experimental dataset, bootstrap out-of-bag validation is employed to ensure methodological robustness. Model-agnostic interpretability, including permutation importance, SHAP analysis, and partial-dependence plots, provides physical transparency and reveals that CR and CCR exert strong yet opposing influences on the composite response, with CCR partially compensating for CR-induced strength losses through enhanced cohesiveness. Differential Evolution (DEoptim) applied to the trained surrogate identifies optimal material proportions within a continuous design space, favouring mixes with 5–10% CCR and limited CR content. Among the evaluated mixes, 0% CR–5% CCR delivers the best overall performance, while 20% CR–5% CCR offers a balanced strength–ductility compromise. Overall, the proposed framework provides a transparent, interpretable, and scalable data-driven pathway for optimising SCC incorporating circular materials under competing performance requirements.