We analyze the Probability of Default (PD) of non-financial corporations in Europe using Random Forests (RF) and assess implications for stress testing the banking sector. To this end, we exploit data on firms’ financial statements (Orbis) and banks’ credit registry (Anacredit). We show that RF displays stronger risk sensitivity than logistic regression in stress testing, shedding new light on the non-linear effect of scenario severity on PD.

Martin Bodenstein and Junzhu ZhaoWe investigate Barro's random walk hypothesis according to which distortionary labor taxes should follow a random walk for any stochastic process of government expenditures, see Barro (1979). When agents experience cognitive discounting as in Gabaix (2020), they perceive government debt as wealth, and the random walk result breaks down except for knife-edge combinations of limited rationality by policymakers and the private sector.

We estimate the cyclical response of labour force participation to growth shocks across EU regions. We use a shift-share instrumental variable approach and local projections on EU Labour Force Survey microdata covering 15 countries and 114 regions over 2000–2020. The aggregate labour force participation rate is remarkably resilient, a clear contrast to the highly cyclical participation rate documented for the U.S. However, this resilience masks pronounced demographic heterogeneity.

Silicon Valley promises abundance, but corporate America is built for extraction. The underlying operating system is stuck on making big shareholders rich the expense of everyone else. It’s time for a reboot. *From the “AI and the Future of the American Worker,” a series on how artificial intelligence is impacting labor, power, and the meaning of work. (Read Part 1 of this article here).