基于集对分析和马尔可夫链的电力客户信用风险评估  

Assessment of power customer credit risk based on set pair analysis and Markov chain model

作　　者：宋连峻[1] 徐志勇[2] 

机构地区：[1]武汉大学经济与管理学院,湖北武汉430070 [2]北京市电力公司,北京100061

出　　处：《电力自动化设备》2009年第12期37-40,共4页Electric Power Automation Equipment

摘　　要：为能更加有效地评估电力客户的信用水平,防范电费回收风险,针对以往电力客户信用风险评价方法只局限于静态评价上的不足,构建了基于集对分析和马尔可夫链的电力客户信用风险评估模型,通过联系度中的同势、均势和反势来判断客户信用风险程度的变化趋势,并用联系度来计算、评估电力客户信用的大小,还可以通过两两时段间的同、异、反转移矩阵计算来预测电力客户下一时段的信用水平,从而实现了对电力客户信用风险的全面、动态评估;最后,通过对某一客户的实际算例可知,所构建的基于集对分析和马尔可夫链的电力客户信用风险评估模型对于动态评价电力客户的信用是科学、有效、切实可行的。The traditional methods of power customer credit risk assessment only carry out the static evaluation. To improve the assessment efficiency and prevent the tariff collection risk,a dynamic assessment model is established based on the set pair analysis and Markov chain,which judges the change tendency of customer credit risk degree according to the equal power,balance power and opposite power of relationship degree,evaluates the current customer credit level with relationship degree,and forecasts the customer credit level of next period by the equal different transferring matrix based on the Markov chain. The comprehensive and dynamic assessment of customer credit risk is thus achieved. A practical example shows that,the model is scientific, effective and feasible.

关 键 词：电力客户 信用评价 集对分析 马尔科夫链 联系度 风险 

分 类 号：F407.61[经济管理—产业经济]