Data mining is the study of how to determine underlying patterns in the data to help make optimal decisions on computers when the database involved is voluminous, hard to characterize accurately, and constantly changing. It deploys techniques based on machine learning, alongside the conventional methods. More importantly, these techniques can generate decision or prediction models, based on the actual historical data. Therefore, they represent true evidence-based decision support. Rainfall prediction is a good problem to solve by these data mining techniques. This paper proposes an improved Naïve Bayes classifier (INCB) technique and explores the use of genetic algorithms (GAs) for selection of a subset of input features in classification problems. It then carries out a comparison with several other techniques. It sets a comparison of the following algorithms, namely: 1) genetic algorithm with average classification or general classification (GA-AC, GA-C), 2) C4.5 with pruning, and 3) INBC with relative frequency or initial probability density (INBC-RF, INBC-IPD) on the real meteorological data in Hong Kong. Two simple schemes are proposed to construct a suitable data set for improving the performance. Scheme I uses all basic input parameters for rainfall prediction. Scheme II uses the optimal subset of input variables which are selected by a GA. The results show that among the methods we compared, INBC achieved about 90% accuracy rate on the rain/no-rain (Rain) classification problems. This method also attained reasonable performance on rainfall prediction with three-level depth (Depth3) and five-level depth (Depth5), which are around 65%-70%.
