In Costa Rica, the Ministry of Finance is using a predictive model designed with data mining techniques to determine the behavioral patterns of companies that might be circumventing tax payments.
Analyzing and crossing checking historical information from multiple databases, the statistical model used by the Directorate General of Taxation attempts to predict which companies are more likely to evade paying taxes depending on their historical behavior measured through transactions, tax returns and other data.By linking all of the information, they identify patterns of behavior similar to those of other companies that have evaded taxes in the past.