A neural network model for cell suppression of tabular data

Cell suppression is a technique commonly used in the publishing of economic data in tabular formats. The sensitive entries, which are called primary suppressions, need to be suppressed. However, suppression of the primary cells alone still allows one to estimate a range for each of the missing values by considering the published entries; additional entries must be suppressed. The authors present a neural network model which seeks to learn which table entries to blank out to guarantee specified levels of protection. The neural network employs backpropagation. The neural network is trained on the solutions from a heuristic, network-based model. The trained network is then used to obtain solutions to other problems. Modeling issues and computational results are discussed