This paper develops a sequential deep learning algorithm for solving dynamic stochastic general equilibrium (DSGE) models. The algorithm trains a deep neural network to approximate the model’s policy functions across four progressive phases: steady-state anchoring, exploration around the steady state, simulation on the ergodic set, and Monte Carlo integration of stochastic expectations.
This paper develops a sequential deep learning algorithm for solving dynamic stochastic general equilibrium (DSGE) models. The algorithm trains a deep neural network to approximate the model’s policy functions across four progressive phases: steady-state anchoring, exploration around the steady state, simulation on the ergodic set, and Monte Carlo integration of stochastic expectations.
Recent stress in parts of the US private credit market − including concerns about exposures in the software sector and redemption pressure in semi-liquid vehicles − has led to renewed focus on possible financial stability risks stemming from private credit and the potential relevance of such risks for the euro area. This special feature looks at the exposure of the euro area financial system to private credit. Using available commercial, public and proprietary data, it finds that euro area financial institutions appear to have limited direct exposure to private credit.
Ryan Byun, Bennett Fees, Margaret M. Jacobson, and Todd B. WalkerCentral bank communications, particularly FOMC statements and press conferences, play a crucial role in shaping financial market expectations. Using large language models to quantify central bank content, this paper demonstrates how sentiment aligns with traditional market-based monetary policy measures. We show that press conferences correlate with future policy to a greater extent than other communications.
Artificial intelligence (AI) is rapidly transforming financial decision-making. To explore the implications for financial stability we ran simulation-based experiments on two different AI architectures. We found that Q-learning algorithms, a form of reinforcement learning, achieved a high degree of coordination, but were prone to bank run-like dynamics. In contrast, large language models , which rely on contextual reasoning, were less prone to such runs but generated heterogeneous and unpredictable behaviour.
Sai MaUsing microdata from the Michigan Survey of Consumers, we study how within-household reallocations of attention across news affect inflation expectation bias, measured relative to a real-time, machine-learning full-information benchmark. Shifting attention toward unfavorable (favorable) economic news increases (decreases) forecast bias substantially, while dropping attention to an unfavorable topic has little effect.
This paper is the first to simultaneously examine firms’ market-based and bank-based external finance premia and investigate the behavior of corporate bond markets in the United States and the euro area, with a focus on country- and state-level heterogeneity in monetary unions. Using a unique micro-level dataset, we show that market finance premia, measured with corporate bond spreads, are remarkably similar in both the euro area and the US in terms of how little they depend on the issuer’s state or country of origin.
We study how private equity (PE) buyouts propagate through supply chains using unique firm-to-firm transactions data from Belgium. In normal times, suppliers of PE-backed firms outperform their peers by 5%–10% in employment and sales growth, primarily due to increased input demand from PE-backed customers rather than knowledge spillovers or other mechanisms. In economic downturns, however, this outperformance is attenuated and suppliers compress markups by around 8% as PE investors intensify bargaining pressure and reconfigure supply chains to extract cost savings.
We study how private equity (PE) buyouts propagate through supply chains using unique firm-to-firm transactions data from Belgium. In normal times, suppliers of PE-backed firms outperform their peers by 5%–10% in employment and sales growth, primarily due to increased input demand from PE-backed customers rather than knowledge spillovers or other mechanisms. In economic downturns, however, this outperformance is attenuated and suppliers compress markups by around 8% as PE investors intensify bargaining pressure and reconfigure supply chains to extract cost savings.
This paper is the first to simultaneously examine firms’ market-based and bank-based external finance premia and investigate the behavior of corporate bond markets in the United States and the euro area, with a focus on country- and state-level heterogeneity in monetary unions. Using a unique micro-level dataset, we show that market finance premia, measured with corporate bond spreads, are remarkably similar in both the euro area and the US in terms of how little they depend on the issuer’s state or country of origin.
