Predicting information systems outsourcing success using a hierarchical design of case-based reasoning

In recent years, much attention has been focused on information systems (IS) outsourcing by practitioners as well as academics. However, our understanding of the factors influencing IS outsourcing success is still incomplete because of lacking empirical results. The attempt to forecast IS outsourcing success using the affecting factors thus becomes challenging. Case-based Reasoning (CBR) is a machine reasoning method that adapts previous similar cases to infer further similarity. CBR method is adopted to analogize IS attributes to the consequences of IS outsourcing practices. This study proposed a two-level feature weights design to enhance CBR's inferencing performance. For effective case retrieval, a Genetic Algorithm mechanism is employed to determine the most appropriate two-level feature weights. One hundred and forty-six real IS outsourcing cases, each with 22 features and eight outcome features are collected as the case base. The proposed approach is compared with the equal weights approach and the regression method. The results indicate that our approach is able to produce more effective prediction outcomes. (C) 2003 Elsevier Ltd. All rights reserved.