Formulating a mix design for 3D concrete printing (3DCP) is challenging, as it involves an iterative approach, wasting a lot of resources, time, and effort to optimize the mix for strength and printability. A potential solution is mix formulation through artificial intelligence (AI); however, being a new and emerging field, the open-source availability of datasets is limited. Limited datasets significantly restrict the predictive performance of machine learning (ML) models. This research explores data augmentation techniques like deep generative adversarial network (DGAN) and bootstrap resampling (BR) to increase the available data to train three ML models, namely support vector machine (SVM), artificial neural network (ANN), and extreme gradient boosting regression (XGBoost). Their performance was evaluated using R², MSE, RMSE, and MAE metrics. Models trained on BR-augmented data showed higher accuracy than those trained on the DGAN-augmented data. The BR-trained XGBoost exhibited the highest R² scores of 0.982, 0.970, 0.972, 0.971, and 0.980 for cast compressive strength, printed compressive strength direction 1, 2, 3, and slump flow respectively. The proposed method of predicting the slump flow (mm), cast, and anisotropic compressive strength (MPa) can effectively predict the mix design for printable concrete, unlocking its full potential for application in the construction industry.