Predicting housing prices is beneficial for both investors and households especially for a large housing market like Miami. Although many scholars have already performed multifarious researches in various locations, no vigorous research on Miami’s housing market is conducted to our knowledge. The purpose of this research is to construct a satisfying predicting model to forecast Miami housing prices that provide reliable references for people in Miami. A number of machine learning methods and deep learning models are implemented in this paper, including SVR, Linear Regression, Random Forest, Neural Network, and XGBoost. Among all models, ensemble learning methods Random Forest and XGBoost produce the best results, the former of which achieved an adjusted R 2 of 0.9234 and XGBoost obtained an adjusted R 2 of 0.9254. Moreover, we also analyze the factors resulting in high housing prices in Miami with the acquired insights from these powerful ensemble learning models.