Search Results
Journal Article
Did Importers Try to Front-Run Recent Tariffs on China?
Because tariffs are a tax on foreign goods, tariffs are thought to reduce imports. However, imports may actually increase after a tariff is announced if importers can stock inventories ahead of the tariff’s implementation. We find that after the announcement of additional tariffs on China in May 2024, imports from China increased by 15 percent for EV batteries, which are difficult to substitute.
Journal Article
Assessing the Risk of Extreme Unemployment Outcomes
Although the unemployment rate is at a historically low level, many policymakers are nevertheless watching projections for the future unemployment rate closely to evaluate the risk of extreme outcomes. We assess the probabilities of extreme outcomes in the near and medium term and find that the risk of unexpectedly high unemployment three years in the future has declined from its Great Recession peak and remained low over the past three years.
Working Paper
What Do LLMs Want?
Large language models (LLMs) are now used for economic reasoning, but their implicit "preferences” are poorly understood. We study LLM preferences as revealed by their choices in simple allocation games and a job-search setting. Most models favor equal splits in dictator-style allocation games, consistent with inequality aversion. Structural estimates recover Fehr–Schmidt parameters that indicate inequality aversion is stronger than in similar experiments with human participants. However, we find these preferences are malleable: reframing (e.g., masking social context) and learned ...
Working Paper
Understanding Models and Model Bias with Gaussian Processes
Despite growing interest in the use of complex models, such as machine learning (ML) models, for credit underwriting, ML models are difficult to interpret, and it is possible for them to learn relationships that yield de facto discrimination. How can we understand the behavior and potential biases of these models, especially if our access to the underlying model is limited? We argue that counterfactual reasoning is ideal for interpreting model behavior, and that Gaussian processes (GP) can provide approximate counterfactual reasoning while also incorporating uncertainty in the underlying ...
Journal Article
Revamping the Kansas City Financial Stress Index Using the Treasury Repo Rate
The Kansas City Financial Stress Index (KCFSI) uses the London Interbank Offered Rate (LIBOR) to measure money market borrowing conditions. But regulatory changes in the United Kingdom will eliminate LIBOR by 2021. We construct a revised financial stress index with a variable that measures the cost of borrowing collateralized by Treasury securities (the Treasury repo rate) instead of LIBOR. {{p}} This revised measure of the KCFSI is highly correlated with the current KCFSI, suggesting the Treasury repo rate can replace LIBOR.
Working Paper
Text Sentiment About Monetary Policy
This paper uses text data from Federal Open Market Committee (FOMC) meeting transcripts to estimate the reference levels of full employment, inflation, and financial conditions perceived by voting members and to uncover time variation in the Taylor rule parameters. We construct topic dictionaries on economic slack, inflation, and financial markets, and infer reference levels from members’ sentiment using a state-space model. The estimated employment reference level indicates that FOMC voting members generally perceived the labor market as tighter than implied by the Congressional Budget ...
Working Paper
Explaining Machine Learning by Bootstrapping Partial Marginal Effects and Shapley Values
Machine learning and artificial intelligence are often described as “black boxes.” Traditional linear regression is interpreted through its marginal relationships as captured by regression coefficients. We show that the same marginal relationship can be described rigorously for any machine learning model by calculating the slope of the partial dependence functions, which we call the partial marginal effect (PME). We prove that the PME of OLS is analytically equivalent to the OLS regression coefficient. Bootstrapping provides standard errors and confidence intervals around the point ...
Working Paper
Explaining Machine Learning by Bootstrapping Partial Marginal Effects and Shapley Values
Machine learning and artificial intelligence are often described as “black boxes.” Traditional linear regression is interpreted through its marginal relationships as captured by regression coefficients. We show that the same marginal relationship can be described rigorously for any machine learning model by calculating the slope of the partial dependence functions, which we call the partial marginal effect (PME). We prove that the PME of OLS is analytically equivalent to the OLS regression coefficient. Boot- strapping provides standard errors and confidence intervals around the point ...
Working Paper
Evaluating Local Language Models: An Application to Bank Earnings Calls
This study evaluates the performance of local large language models (LLMs) in interpreting financial texts, compared with closed-source, cloud-based models. We first introduce new benchmarking tasks for assessing LLM performance in analyzing financial and economic texts and explore the refinements needed to improve its performance. Our benchmarking results suggest local LLMs are a viable tool for general natural language processing analysis of these texts. We then leverage local LLMs to analyze the tone and substance of bank earnings calls in the post-pandemic era, including calls conducted ...
Journal Article
Testing Hybrid Forecasts for Imports and Exports
The quality of economic forecasts tends to deteriorate during times of stress such as the COVID-19 pandemic, raising questions about how to improve forecasts during exceptional times. One method of forecasting that has received less attention is refining model-based forecasts with judgmental adjustment, or hybrid forecasting. Judgmental adjustment is the process of incorporating information from outside a model into a forecast or adjusting a forecast subjectively. Hybrid forecasts could be particularly useful during extraordinary times such as the COVID-19 pandemic, as models that do not ...