Information Gain with Weight Based Decision Tree for the Employment Forecasting of Undergraduates

With the rapid increasing of the number of undergraduates in China, employment has become one of the greatest social concerns. In order to help the undergraduates improve their employment abilities, it is necessary to analyze the relationship between the undergraduates´ employment situation and their performances such as academic records, reading status, and so on. However, it is difficult to identify these performances and their influence to the employment. Therefore, a novel method named IGWDT(Information Gain with Weight based Decision Tree) is proposed, in which the feature selection is employed to get the most relative performances and IGW (Information Gain with Weight) is defined to improve the information gain and be used to indicate the degree of influence of different performance, furthermore the values of IGW are acquired by using genetic algorithm. The experiments on sample undergraduates show that the proposed method can get good results to help undergraduates improve their employment abilities and it performs better than the compared methods on prediction accuracy.