Scientists from the Higher School of Economics and University of Valladolid have developed a neural network that can predict corruption based on economic and political factors.
The researchers, Félix J. López-Iturriaga and Iván Pastor Sanz, used self-organizing maps (SOMs), a kind of artificial neural network that aims to mimic brain functions, to predict corruption cases by detecting patterns within large amounts of data. They looked at data from actual cases of corruption cases in Spain, using the neural network to look at the probability of corruption cases in different time scenarios. The hope is that this will lead to anti-corruption measures that can be tailored “depending on the immediacy of such corrupt practices.”
They published their results, “Predicting Public Corruption with Neural Networks: An Analysis of Spanish Provinces” in Social Indicators Research, showing that economic factors, particularly taxation of real estate, economic growth, increased house prices, and the growing number of deposit institutions and non-financial firms may induce public corruption. They also find that when the same party remains in power for too long they are more likely to become corrupt. Keep that in mind when voting in the 2018 elections.
Recognize your brand’s excellence by applying to this year’s Brands That Matter Awards before the early-rate deadline, May 3.
