Schröter, AdrianZimmermann, ThomasZeller, Andreas2023-05-222023-05-222006https://dl.gi.de/handle/20.500.12116/41602In an empirical study of 52 ECLIPSE plug-ins, we found that the software design as well as past failure history, can be used to build support vector machines which accurately predict failure-prone components in new programs. Our prediction only requires usage relationships between components, which are typically defined in the design phase; thus, designers can easily explore and assess design alternatives in terms of predicted quality.enText/Journal Article0720-8928