基于多准则决策方法的数据资产质量评价模型

A Data Asset Quality Evaluation Model Based on a Multi-criteria Decision-making Method

摘要:

结合最优最劣法（best worst method，BWM）、三角模糊数和逼近理想解排序（TOPSIS）方法，提出了一种用于评估数据资产质量的多准则决策框架。首先通过专家访谈构建评价指标体系。其次，采用BWM方法确定评价指标的权重信息。随后，邀请专家根据指标对数据资产质量进行语言评价，并引入三角模糊数克服单个实数表达不完整问题。最后，根据评价指标权重及专家评价信息，采用TOPSIS方法对数据资产质量进行排序。通过将提出的方法应用于商业银行的数据资产质量评估， 验证方法的可行性。

Abstract:

This paper proposes a multi criteria decision making （MCDM） framework for evaluating the quality of data assets by combining the best worst method （BWM）， technique for order preference by similarity to an ideal solution （TOPSIS） and triangular fuzzy number. In this framework， firstly， the evaluation indexes are constructed through expert interviews. Then， the BWM method is used to determine the weight of the evaluation indexes. After that， experts are invited to linguistically evaluate the quality of the data set based on the constructed indexes， and triangular fuzzy numbers are introduced to overcome the problem of incomplete expression of individual real numbers. Finally， the TOPSIS method is utilized to rank the quality of the data assets. The feasibility of the methodology is verified by applying the proposed approach to data asset quality assessment of commercial banks.