A Gini Index Based Elegant Decision Tree Classifier to Predict Precipitation

Water is one of the most important of nature´s gifts to the living creatures on Earth. Rainfall is one form of precipitation, and it primarily depends on humidity, temperature, pressure, wind speed, dew point, and so on. The present research is focused on using the gini index as an attribute selection measure in an elegant decision tree to predict precipitation for voluminous datasets. This study aims at improving the prediction of precipitation over the supervised learning in a Quest decision tree, especially when the datasets are large. A decision tree using the gini index increases the accuracy rate while decreasing computational time by reducing the computation of total split points. This approach provides an average accuracy of 72.98% with a reduction of 63% in computational time over a SLIQ decision tree.