<p>Increasing requirements for sustainable building materials have also intensified the need to identify alternative cementitious materials that can mitigate environmental problems associated with traditional cement production. This study aims to investigate the possibility of using agro-industrial waste materials, namely wheat husk ash (WHA), chana husk ash (CHA), and artificial sand waste (ASW), as alternatives to conventional concrete materials. A set of concrete mixes was prepared with varying percentages of these materials to evaluate their impact. Various tests, including compressive strength, split tensile strength, flexural strength, acid resistance, carbonation depth, and rapid chloride permeability, were conducted. The results showed that the addition of these materials to concrete enhanced its microstructure and durability due to enhanced pozzolanic reactions. The results also indicated that a combination of 8% WHA, 5% CHA, and 2% ASW, totaling a replacement of 15%, was found to provide optimum overall performance considering both mechanical strength retention and enhanced durability characteristics. To further improve the predictive accuracy, various machine learning models such as linear regression, support vector regression, random forest, gradient boosting, artificial neural networks, and extreme gradient boosting (XGBoost) were developed for the prediction of the compressive strength. Among the models, the XGBoost model showed the best accuracy for the prediction with an <i>R</i>² value of 0.95 and the least error metrics. SHAP was also used for the interpretation of the contribution of the input variables toward the prediction. The results show the suitability of agro-industrial waste materials for the production of sustainable concrete.</p>