Research Of Decision Tree Classification And Its Application To Tax Assessment

Data Mining (DM) aims at analyzing massive amounts of data and extracting meaningful and comprehensible patterns, called knowledge. In recent years, DM has got domestic and international widespread concern and has been becoming most hot researching realm in the field of information systems and computer science. DM has been widely used in biomedical field, financial field, retail industry and telecommunication industry. Based on through exploring and analysis on the related literatures, the state-of-the-arts of knowledge and data mining, the main contents and key technologies are generalized and summarized, The development trends, questions, and further tasks are particularly commented on DM. This paper puts forward three strategies to improve C4.5 algorithm. According to characteristics of data the new algorithm selects the optimum strategy. Based on the UCI Knowledge Discovery in Databases Archive and UCI Machine Learning Archive as experiment data, this paper compares C4.5 with QC4.5(the new algorithm) on the execution efficiency, and it can be see that QC4.5 is better than C4.5. The main works in this paper as follows:1. Research the concept of and development in data mining, the process of data mining, the classification of data mining.2. Research the decision tree, and particularly expound the constructor algorithm, split criterion, pruning criterion etc.3. Research C4.5 algorithm, and put forward three strategies to improve C4.5 algorithm.4. Imply QC4.5 algorithm to the system of attitude tax assessment for predictive model, and make a good effect in practice.The novel idea in this paper is that: in the process of constructing decision tree, according the characteristic of data select the optimum strategy to find the split attribute. This method can improve the execution efficiency of C4.5 in trial and is doable.