Can machine learning support better governance? In the context of Brazilian municipalities, 2001-2012, we have access to detailed accounts of local budgets and audit data on the associated fiscal corruption. Using the budget variables as predictors, we train a tree-based gradient-boosted...

Can machine learning support better governance? In the context of Brazilian municipalities, 2001-2012, we have access to detailed accounts of local budgets and audit data on the associated fiscal corruption. Using the budget variables as predictors, we train a tree-based gradient-boosted...

Can machine learning support better governance? In the context of Brazilian municipalities, 2001-2012, we have access to detailed accounts of local budgets and audit data on the associated fiscal corruption. Using the budget variables as predictors, we train a tree-based gradient-boosted...

Can machine learning support better governance? In the context of Brazilian municipalities, 2001-2012, we have access to detailed accounts of local budgets and audit data on the associated fiscal corruption. Using the budget variables as predictors, we train a tree-based gradient-boosted...

In this paper, we estimate the effect of the 1918 Influenza pandemic on income inequality in Italian municipalities. Our identification strategy exploits the exogenous diffusion of influenza across municipalities due to the presence of infected soldiers on leave from World War I operations at...

We explore the effects of exposure to conflict and violence on civic compliance with the law. Using newly digitized historical records of income declarations and tax audits from post-World War I Italy, we show that losing a relative as a direct result of the war reduces tax compliance. To...

We explore the effects of exposure to conflict and violence on civic compliance with the law. Using newly digitized historical records of income declarations and tax audits from post-World War I Italy, we show that losing a relative as a direct result of the war reduces tax compliance. To...