V-MDAV: A multivariate microaggregation with variable group size. Microaggregation is a clustering problem with minimum size constraints on the resulting clusters or groups; the number of groups is unconstrained and the within-group homogeneity should be maximized. In the context of privacy in statistical databases, microaggregation is a well-known approach to obtain ing anonymized versions of confidential microdata. Optimally solving microaggregation on multivariate data sets is known to be difficult (NP-hard). Therefore, heuristic methods are used in practice. This paper presents a new heuristic approach to multivariate microaggregation, which provides variable-sized groups (and thus higher within-group homogeneity) with a computational cost similar to the one of fixed-size microaggregation heuristics.
Keywords for this software
References in zbMATH (referenced in 4 articles )
Showing results 1 to 4 of 4.
- Casino, Fran; Domingo-Ferrer, Josep; Patsakis, Constantinos; Puig, Domènec; Solanas, Agusti: A $k$-anonymous approach to privacy preserving collaborative filtering (2015)
- Aloise, Daniel; Hansen, Pierre; Rocha, Caroline; Santi, Éverton: Column generation bounds for numerical microaggregation (2014)
- Oommen, B.John; Fayyoumi, Ebaa: On utilizing dependence-based information to enhance micro-aggregation for secure statistical databases (2013)
- Schneeweiss, Hans; Rost, Daniel; Schmid, Matthias: Probability and quantile estimation from individually micro-aggregated data (2012)