Communications of the ACM
Beyond Encryption: Protecting Consumer Privacy While Keeping Survey Results Accurate
Drexel and Vanderbilt university researchers have proposed a new technique for permanently altering survey datasets to shield consumers privacy.
Credit: Drexel.edu
Researchers at Drexel and Vanderbilt universities have proposed a new technique for permanently altering survey datasets to shield consumers’ privacy, while retaining a reasonable degree of accuracy.
Drexel's Matthew Schneider and Vanderbilt's Dawn Iacobucci analyzed a survey dataset collected in 2015 by the city of Austin, TX, and released to the public following an Open Data movement.
For a survey of the city's Asian-Americans, each respondent was asked their ethnic origin, which had 32 categories; age, which had 77 categories; zip code, which had 61 categories; and gender.
The researchers based their technique on a method used in genomic sequencing applications that conceals consumers' identity while maintaining the accuracy of insights within 5%.
Schneider said the methodology basically "shuffles" the dataset's demographic data, but only "when it maintains the correlations between important variables that are essential to analysts."
From Drexel Now
View Full Article
Abstracts Copyright © 2020 SmithBucklin, Washington, DC, USA
No entries found