The quality and durability of any structure depends upon the mechanical property of the concrete that is concrete compressive strength. The concrete strength relates to its influencing factors such as the quality and proportions of the binding materials, aggregates, water and admixtures. This paper proposes to use machine learning aided approach to predict concrete compressive strength which is required for construction applications determined on the factors/attributes such as cement, blast surface slag, superplasticizer, fly ash, water, age, coarse and fine aggregate. For this study, 1030 samples were collected and utilized with varying proportions of 8 attributes and used both bagging and boosting regression ensemble machine learning algorithms. The regression models: Bagging Regressor, Extra Tree Regressor, Adaboost regressor, Random Forest Regressor, Gradient boosting and Histogram gradient boosting regressor developed were created and tested to find compressive strength of the concrete and also to identify the significant attribute effecting the concrete compressive strength. The performance of the models was quantitatively evaluated and compared. The experimental results and their analysis using the metrics, Explained Variance Score, Mean Absolute Error, R2 and Mean Square Error showed a better performance from histogram gradient boosting regressor and indicated age as a significant influencing factor that plays key role towards the concrete compressive strength.