<p>For the optimization of concrete mixture proportion, multiple objectives are selected in this study, such as maximizing the compressive strength of the concrete while simultaneously minimizing the cost of the concrete mixture. This optimization is done under various constraints so that a practically feasible mixture can be obtained. For the present study, 1456 concrete mix data have been used to develop the model. Firstly, a predictive model has been chosen as the first objective function for multiobjective optimization (MOO) by analyzing the performance matrix of four models (XGBoost, CatBoost, RF, and LightGBM). The model’s hyperparameters were optimized using Gridsearch with cross validation. Secondly, a cost function has been developed as a second objective function by using the unit cost of each material constituent. Lastly, the MOO is applied with some constraints, and consequently, a Pareto front has been developed to find out the feasible solution, and TOPSIS is used to find out the optimum solution. CatBoost demonstrated the best generalization with an R² of 0.8816. The selected model is integrated in a multi-objective optimization framework using NSGA-II, with cost as the second objective function and constraints. The study incorporates realistic engineering constraints ensuring that all generated mixtures remain practical and construction ready. From many feasible solutions, one solution is selected which achieved a predicted compressive strength (CS) of 56.49 MPa at a cost of INR 5,273.39 per cubic meter.</p>