Reuse is as an important approach to conceptual object-oriented design. A number of reusable artifacts and methodologies to use these artifacts have been developed that require the designer to select to a certain level of granularity and a certain paradigm. This makes retrieval and application of these artifacts difficult and prevents the simultaneous reuse of artifacts at different levels of granularity. The purpose of this research, therefore, is to develop an actionable approach to lowering barriers to reuse. The approach is materialized in automating the conceptual design stage of the systems development process by reusing a new kind of design artifacts, which we call design fragments, which are synthesized with analysis patterns. The goal of the study includes the development of machine learning algorithms generating reusable design fragments and effectively storing/retrieving them.