OBJECTIVES: The objective of this presentation will be to introduce the audience to various data dimension reduction techniques that may be applied in the setting of a large commercial claims data set to facilitate the task of identifying important factors or key features for use in subsequent analysis.   METHODS: The author will provide a brief survey of the data dimension reduction literature from areas as diverse as image analysis, neural networks, gene expression microarrays, and high through-put chemistry to demonstrate that despite that many of these techniques have been used in other settings or areas of research, their application to the analysis of health care claims data is relevant and potentially quite useful.  RESULTS: One, all-purpose, optimal data dimension technique does not exist for application in the analysis of health care claims data.  The analyst needs to weigh the features of the large data set under consideration, the objectives of the downstream or subsequent analysis, and the availability of tools for ease of use and interpretation of results.    CONCLUSIONS:  The number of data dimension reduction techniques available to claims data set researchers is large and diverse; however, keys features of these various approaches can help the analyst make an informed decision that is effective with some simple setting and objectives diagnosis.