Cluster analysis of heterogeneous rank data

Cluster analysis of ranking data, which occurs in consumer questionnaires, voting forms or other inquiries of preferences, attempts to identify typical groups of rank choices. Empirically measured rankings are often incomplete, i.e. different numbers of filled rank positions cause heterogeneity in the data. We propose a mixture approach for clustering of heterogeneous rank data. Rankings of different lengths can be described and compared by means of a single probabilistic model. A maximum entropy approach avoids hidden assumptions about missing rank positions. Parameter estimators and an efficient EM algorithm for unsupervised inference are derived for the ranking mixture model. Experiments on both synthetic data and real-world data demonstrate significantly improved parameter estimates on heterogeneous data when the incomplete rankings are included in the inference process.

Inserting innovations in-service

Military platforms have exceptionally long lifecycles and given the state of defense budgets there is a significant trend in sustaining the operational capability of legacy platforms for much greater periods than originally designed. In the context of through-life management, one of the key questions is how to manage the flow of technology for platform modernization during the in-service phase of the lifecycle? Inserting technological innovations in-service is achieved through technology insertion processes. Technology insertion is the pre-eminent activity for both maintaining and enhancing the functional capability of a platform especially given the likely changes in future military operations, the pace of change in technology and with the increasing focus on lifecycle cost reduction. This chapter provides an introduction to technology insertion together with an overview of the key issues that practitioners are faced with. As an aid to planning technology insertion projects, a decision-support framework is presented. © 2010 Springer-Verlag Berlin Heidelberg.