Rapidly intensifying (RI) tropical cyclones (TC) are the major error sources in TC intensity forecasting. In order to improve the estimates of RI probability, association rules as a data mining technique are used here to facilitate the process of looking for candidate sets of conditions which have strong interactions with rapidly intensifying TCs. Compared to the relation analysis method, the technique of association rules can simply explore associations among multiple conditions. Moreover, our mining results identified a reduced predictor set with fewer factors but improved probabilities of RI estimates compared to the results based on relation analysis. For a given number of constraints affecting the RI process, the data mining technique can identify the combination of the factors which give the largest RI probabilities. In this paper, we will present the main findings based on the data for SHIPS (Statistical Hurricane Intensity Prediction Scheme), an operational statistical-dynamical hurricane intensity forecasting model.