Decision Tree Model Based On Generalized Information Entropy And Its Application In Performance Evaluation

Performance evaluation plays a vital role in business management, how to implement effectively the performance evaluation has became an important issue in human resource management. Now, there are many methods in implementing performance evaluation, such as graphic rating scale, alternative ranking method, paired comparison method, critical incident method, behavioral observation scale, management by objectives, 360-degree evaluation method, key performance indicators, balanced score card and so on.. But these methods can only get some surface information of data, can not better tap the potential correlation between the data. Then data mining methods which is represented by decision tree algorithm are used in performance evaluation effectively compensate for this lack. While because fuzzy decision tree effectively integrates the advantages of fuzzy theory and decision trees, not only have a strong decision analysis ability, but also can better handle the ambiguity and uncertainties of the data, so it is more and more concerned as the extension of decision tree.This thesis shows a generating Hartley measure model and its formulas based on the decomposition theorem of fuzzy information through the combination strategy of level cut set and level weight function; then proposes a generalized information entropy fuzzy decision tree model through applying the generalized information entropy into the selection of extended properties(i.e. GFID3); then combined with the choice case of sports activities based on weather, we analysis the properties of GFID3 from different angles and dimensions; at the last, GFID3 is be used in employee perfomance evaluation case, the rule knowledge provides reference basis for enterprise performance management, the results show that GFID3 has good structural characteristics and operational, and can make up for the lack of the current fuzzy decision tree model which can not effectively deal with different decision-making sense, which can be applied in a wide area, such as customer satisfaction evaluation, customer relationship management, economic analysis, complex systems optimization, artificial intelligence and so on.