Abstract Data mining is based on data files which usually contain errors in the form of missing values. This paper focuses on a methodological framework for the development of an automated data imputation model based on artificial neural networks. Fifteen real and simulated data sets are exposed to a perturbation experiment, based on the random generation of missing values. These data set sizes range from 47 to 1389 records. A perturbation experiment was performed for each data set where the probability of missing value was set to 0.05. Several architectures and learning algorithms for the multilayer perceptron are tested and compared with three classic imputation procedures: mean/mode imputation, regression and hot-deck. The obtained results, considering different performance measures, not only suggest this approach improves the quality of a database with missing values, but also the best results are clearly obtained using the Multilayer Perceptron model in data sets with categorical variables. Three learning rules (Levenberg–Marquardt, BFGS Quasi-Newton and Conjugate Gradient Fletcher–Reeves Update) and a small number of hidden nodes are recommended.