分析与支持反腐政策的机器学习方法
A Machine Learning Approach to Analyze and Support Anticorruption Policy
American Economic Journal: Economic Policy · 2025 · [{"name": "Elliott Ash", "affiliation": ["Center for Economic and Policy Research", "ETH Zurich"]}, {"name": "Sergio Galletta", "affiliation": ["ETH Zurich"]}, {"name": "Tommaso Giommoni", "affiliation": ["University of Amsterdam"]}]
中文摘要
机器学习能否支持更好的治理？本研究使用一种基于树的梯度提升分类器，以预算数据作为预测变量，预测巴西市镇的腐败程度。训练后的模型提供了一个腐败的预测性度量，我们通过复制并拓展已有的腐败研究对其进行了验证。我们的政策模拟表明，机器学习能够显著提升腐败检测能力：与随机审计相比，在相同审计率下，机器引导的定向政策能够识别出几乎两倍数量的腐败市镇。（JEL C45, D73, H70, H83, K42, O17）
Abstract
Can machine learning support better governance? This study uses a tree-based, gradient-boosted classifier to predict corruption in Brazilian municipalities using budget data as predictors. The trained model offers a predictive measure of corruption, which we validate through replication and extension of previous corruption studies. Our policy simulations show that machine learning can significantly enhance corruption detection: Compared to random audits, a machine-guided targeted policy could detect almost twice as many corrupt municipalities for the same audit rate. (JEL C45, D73, H70, H83, K42, O17)