【摘要】 IT项目组合中的关联关系使得组合中风险的传播不仅取决于单个项目本身的风险水平,还取决于项目在组合中的相对重要程度。为此,基于复杂网络和自组织映射网提出了一种新的项目重要度评估方法,便于进一步分析组合风险。新方法基于复杂网络建立项目组合的网络模型以表述项目间的关联关系,根据节点项目在模型中的多项指标,采用熵权法确定指标权重,再通过自组织映射网络处理指标信息对节点进行自动聚类,计算其风险水平,确定其重要程度。通过风险传播模型的仿真结果表明,上述方法能够有效评估节点的重要度,对所建议的重要节点项目实施风险控制可以较好地抑制风险的传播。更多还原

【Abstract】 The risk spreading in the IT project portfolio is related not only to the risk level of the single project but also to the relative importance of the project due to the interdependence in the portfolio.In order to evaluate the importance of projects,a new method is proposed based on the complex network and the Self-organizing map(SOM),which can be used to further analyze the portfolio risk.In this method,the network model of the project portfolio is established using the complex network to express the relationship among the projects.According to the multiple indicators of the node project in the model,the entropy weight method was used to determine the weight of indicators,and then the nodes were automatically clustered through the SOM.Thus the risk level of the projects can be calculated and the importance can be ranked.The simulation results of the risk spread model show that the method can effectively evaluate the importance of the nodes,and the implementing risk control on the proposed important node projects can provide a better way to inhibit the spread of risk.更多还原