Accurate determination of the capacity of reinforced concrete (RC) beams in shear remainsrna demanding problem due to its complex failure mechanism and the nonlinear relationshiprnbetween different factors influencing the shear capacity. This research employs differentrntypes of single and ensemble machine learning (ML) based techniques; namely, decisionrntree, support vector machine, extremely randomized trees, gradient boosting, randomrnforest, and extreme gradient boosting (xgBoost) to correctly predict the shear capacity ofrnreinforced concrete beams. To this end, a dataset of experimental test results of RC beamrnwith and without stirrups comprised of various beam geometry, concrete strength,rnreinforcing steel strength, longitudinal and shear reinforcement ratios, and shear span-toeffectiverndepth ratio is used to develop the models.rnThe proposed models were calibrated for different values of hyperparameters to achievernoptimized ML models. The results of the analysis evidenced that the xgBoost model canrnbe effectively utilized to predict the shear capacity of RC beams. The comparison of thernpredictions of the proposed and existing models evidenced that the efficiency of thernproposed model is superior to the existing models and guidelines in terms of accuracy,rnsafety, and economic aspects with significantly lowest bias and variability.rnA solid correlation exists between the shear capacities predicted using the proposed modelrnand the corresponding experimental values as evidenced by the value of ï¿½ï¿½2 (ï¿½ï¿½2 = 0.99)rnfor RC beams without stirrup and (ï¿½ï¿½2 = 0.995) for RC beams with stirrup.rnThe proposed xgBoost model is deployed into a user-friendly web-based application tornfacilitate a quick and accurate prediction of capacity of RC beams in shear. The web-basedrnapplication can be used by both practitioners and researchers to accurately predict the shearrncapacity of beams.