The coalcrete, a new supporting material produced by jet grouting (JG) technique was firstly studied for improving soft coal mass to support roadways in Guobei coal mine, China. Young's modulus is an essential indicator to evaluate the deformation-resisting ability of coalcretes. In this study, for determining Young's modulus of coalcretes efficiently, an intelligent technique was proposed using the support vector machine (SVM) and beetle antennae search (BAS). The hyper-parameters of SVM were firstly tuned by BAS, and then the SVM-BAS model with optimum hyper-parameters was employed to model the non-linear relationship between the inputs (coal content, water content, cement content, and curing time) and output (Young's modulus). By combining these variables, 360 coalcrete samples in total were prepared and tested for establishing the dataset. The results show that BAS is more reliable and efficient than the trial–and–error tuning method. Moreover, by comparison with other baseline models such as back-propagation neural network (BPNN), logistic regression (LR) and multiple linear regression (MLR), the optimized SVM-BAS model is more reliable, accurate and less time consuming for predicting Young's modulus of coalcretes. Besides, by conducting sensitivity analysis (SA), the importance of different input variables was determined. This pioneering work provides guidelines for predicting Young's modulus of coalcretes and designing proper JG parameters in engineering applications.