基于模糊贝叶斯的改进决策方法在企业评价中的应用

The Application of the Improved Decision-Making Method Based on Fuzzy Bayes in the Enterprise Evaluation

朴素贝叶斯算法是数据挖掘领域最简单的分类算法之一。为了让朴素贝叶斯能够灵活地处理连续型数据,分类过程就需要对数据进行离散化处理。而使用模糊数学理论来解决离散化问题是一个不错的选择。因此本文考虑将这两种方法结合,同时在去模糊化过程中引用了一种新型去模糊化方法("内心法"),从而生成一种新的模糊贝叶斯混合模型。并通过一个企业评价实例简单地验证了模糊贝叶斯算法在应对连续性数据时具有良好、可靠的分类效果。

The Naive Bayes algorithm is a simple and lucid classification way in the field of data mining.When meetingwith continuous data,the algorithm usually needs to make discretization in its classifying process.Luckily,the applicationof relevant theories about fuzzy mathematics is a good choice to solve the discretization problem.Thus,this study decidesto make a combination of the Naive Bayesian algorithm and fuzzy mathematics to generate a hybrid model and,in themeanwhile,introduces a new defuzzification method(named as The incenter of area)in the classification process.Through anapplication case of enterprise evaluation,the fuzzy Bayesian hybrid algorithm has been proved to be effective and reliable inthe process of classification for continuous data.