AutoSynth Index: A Synthetic Indicator for Socio-Economic Development Based on Autoencoders

In this work, we propose a novel use for neural networks to build socioeconomic indicators, encoding a possible large information set, within single or multiple synthetic indexes, we call this proposal AutoSynth. In particular, we encode such information using an autoencoder, a neural network method to represent in a lower dimensionality space a matrix of features. We apply such a method to the evaluation of socio-conomic developments of suburban areas in Florence, and we test the performance of our model against some golden standard methods using a stress test.