期刊名称：Euro Area Balance of Payments and International Investment Position Statistics
印刷版ISSN：1830-3420
电子版ISSN：1830-3439
出版年度：2014
出版社：European Central Bank
摘要：This paper aims at providing policymakers with a set of early warningindicators helpful in guiding decisions on when to activate macroprudentialtools targeting excessive credit growth and leverage. To robustlyselect the key indicators we apply the “Random Forest” method,which bootstraps and aggregates a multitude of decision trees. Onthese identified key indicators we grow a binary classification treewhich derives the associated optimal early warning thresholds. Byusing credit to GDP gaps, credit to GDP ratios and credit growthrates, as well as real estate variables in addition to a set of other conditioningvariables, the model is designed to not only predict bankingcrises, but also to give an indication on which macro-prudential policyinstrument would be best suited to address specific vulnerabilities
关键词：Early Warning Systems; Banking Crises; Macroprudential;Policy; Decision Trees; Random Forest
