Using A.I. and street-view images for estimating socio-economic indicators

Using A.I. and street-view images for estimating socio-economic indicators

Monitoring socio-economic indicators such as income inequality or deprivation represents a big challenge even for advanced economies. Nowadays it is mainly tackled by running reliable, but infrequent and costly census campaigns. The emergence of vast and organized online datasets combined with recent advances on machine learning algorithms open an opportunity to explore alternative fast and cheap estimations that could complement traditional demographic and economic measures.

Here I will present a methodology that uses a set of visual features extracted from street-view pictures. We have successfully used this methodology for predicting the income distribution using Google Street View pictures in 6 different cities all over the world. Now, we plan to use the same methodology to predict the deprivation indices all over UK using crowdsource imagery platforms.

Our aim is to be able to build models accurate enough that we can export this technology to places and countries where such level of statistics is still scarce or indicators at small-area level are not available.

Speaker

Mario Gutiérrez-Roig, University of Essex

How to attend

If not a member of the Dept. Mathematical Science at the University of Essex, you can register your interest in attending the seminar and request the Zoom’s meeting password by emailing Dr Osama Mahmoud (o.mahmoud@essex.ac.uk).