An Approach to Prediction of Precipitation Using Gini Index in SLIQ Decision Tree

Prediction of rainfall is the essential problem to be solved. The variation in the rainfall is primarily attributed to its association with Humidity, Temperature, Pressure, Wind Speed and Dew Point etc. Several works have been done in this field over the past few decades. An accurate prediction of rainfall events can aid in accurate financial planning of the economy of nation. The unpredictable natural disasters like floods and droughts not only affected the economy of a country but also the lifestyle of people of the countryside. Data mining is a influential approach which helps in extracting hidden information from huge databases and allows decisions to be taken on knowledge mining basis. This paper highlights Supervised Learning in Quest (SLIQ), decision tree algorithm using Gini Index in order to predict the precipitation with an accuracy of 72.3% and is completely based on the historical data. The decision tree is constructed and the classification rules are generated.