The accurate prediction for the tropical cyclone (TC) intensity is a recognised challenge. Researchers usually develop dynamical models to address this task. However, since the TC intensity is highly influenced by various factors such as ocean and atmosphere conditions, it is difficult to build the very model which can explicitly describe the mechanism of TC. A new idea is developed, utilising the massive historical observation data by a deep learning approach, to conduct a completely data-driven TC intensity prediction model. All the TC intensity and track data which have been observed in Western North Pacific since 1949 are collected, and recurrent neural network for TC intensity prediction is constructed. In general, their motivation as well as novelty is to develop a data-driven approach instead of empirical models. There are very few researches similar to their exploratory work. The proposed method has presented 5.1 ms error in 24 h prediction, which is better than some widely used dynamical models and is close to subjective prediction.