Publications
”A Machine learning approach in stress testing US bank holding companies”, (accepted), International Review of Financial Analysis, /016/j.irfa.2024.103476
Working Papers
”On bank credit and business cycle from a machine learning perspective,” joint with Dalibor Stevanovic
This paper proposes identifying the bank’s credit supply shock using a machine learning approach in a data-rich setup. The analysis consists of two steps. First, we do a pseudo-out-of-sample forecasting exercise to approximate the bankers’ predictive model of the capital-to-asset ratio. Then, we define the aggregate credit shock as the weighted average of bank-specific out-of-sample forecast errors. In the second step, we include the constructed shock in a VAR to assess its impact on the business cycle. We find that a one standard deviation negative aggregate credit shock moves credit volume and prices in the opposite direction, corroborating that it identifies a bank credit supply shock. Furthermore, this shock has significant macroeconomic effects. It triggers a slowdown in GDP growth, inflation, and a substantial commercial and industrial credit volume drop. However, the decline in commercial and industrial credit is more pronounced and persistent than the slowdown in GDP growth.
”Bank-level uncertainty and the business cycle: Evidence from large US Bank holding companies”
This paper introduces a novel method to quantify bank-level uncertainty from forecast errors of a bank’s return on asset (ROA) derived from an ensemble of machine learning models combined with granular bank data and an extensive macroeconomic dataset. From various ROA forecasts, I compute the optimal forecast errors from the average prediction across models. Then, I define the bank-level uncertainty measure as the standard deviation of these forecast errors. Using Vector Autoregression (VAR) analysis, the paper shows that this measure significantly influences both business cycles and credit markets. Unanticipated spikes in bank-level uncertainty lead to notable economic downturns and worsened credit conditions, exceeding the predictive power of conventional macroeconomic and financial uncertainty metrics. These findings advocate for targeted regulatory action in the banking sector to enhance financial stability.