Christopher Kurz
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Christopher Kurz has a total of 9 co-authors. Here are the top co-authors by number of shared publications:
- Leland D. Crane
Board of Governors of the Federal Reserve System (U.S.)
2 shared publications - Paul E. Soto
Board of Governors of the Federal Reserve System (U.S.)
2 shared publications Tomaz Cajner
Board of Governors of the Federal Reserve System (U.S.)
2 shared publicationsBetsy Vrankovich
Board of Governors of the Federal Reserve System (U.S.)
1 shared publication- Betsy Vrankovich
Board of Governors of the Federal Reserve System (U.S.)
1 shared publication Geng Li
Board of Governors of the Federal Reserve System (U.S.)
1 shared publication
Latest Publications
- 1 October 2026
- Published by Board of Governors of the Federal Reserve System in FEDS Notes
- No. 2026-10-01
Pricing Sentiment: Measuring Input Cost Pressure from ISM Survey Responses
Recent history has shown that input cost shocks can propagate quickly and broadly across sectors. When supply chain disruptions, commodity price swings, and demand shocks raise the prices firms pay for materials and services, those pressures can pass through to downstream consumers.
- 1 October 2026
- Published by Board of Governors of the Federal Reserve System in FEDS Notes
- No. 2026-10-01
Pricing Sentiment: Measuring Input Cost Pressure from ISM Survey Responses
Recent history has shown that input cost shocks can propagate quickly and broadly across sectors. When supply chain disruptions, commodity price swings, and demand shocks raise the prices firms pay for materials and services, those pressures can pass through to downstream consumers.
- Open Access
- 1 May 2024
- Published by Board of Governors of the Federal Reserve System in Finance and Economics Discussion Series
- No. 2024-026,p. 1-46
Manufacturing Sentiment: Forecasting Industrial Production with Text Analysis
This paper examines the link between industrial production and the sentiment expressed in natural language survey responses from U.S. manufacturing firms. We compare several natural language processing (NLP) techniques for classifying sentiment, ranging from dictionary-based methods to modern deep learning methods. Using a manually labeled sample as ground truth, we find that deep learning models partially trained on a human-labeled sample of our data outperform other methods for classifying the sentiment of survey responses. Further, we capitalize on the panel nature of the data to train models which predict firm-level production using lagged firm-level text. This allows us to leverage a large sample of "naturally occurring" labels with no manual input. We then assess the extent to which each sentiment measure, aggregated to monthly time series, can serve as a useful statistical indicator and forecast industrial production. Our results suggest that the text responses provide information beyond the available numerical data from the same survey and improve out-of-sample forecasting; deep learning methods and the use of naturally occurring labels seem especially useful for forecasting. We also explore what drives the predictions made by the deep learning models, and find that a relatively small number of words associated with very positive/negative sentiment account for much of the variation in the aggregatesentiment index.
- 1 May 2024
- Published by Board of Governors of the Federal Reserve System in Finance and Economics Discussion Series
- No. 2024-026,p. 1-46
Open AccessManufacturing Sentiment: Forecasting Industrial Production with Text Analysis
This paper examines the link between industrial production and the sentiment expressed in natural language survey responses from U.S. manufacturing firms. We compare several natural language processing (NLP) techniques for classifying sentiment, ranging from dictionary-based methods to modern deep learning methods. Using a manually labeled sample as ground truth, we find that deep learning models partially trained on a human-labeled sample of our data outperform other methods for classifying the sentiment of survey responses. Further, we capitalize on the panel nature of the data to train models which predict firm-level production using lagged firm-level text. This allows us to leverage a large sample of "naturally occurring" labels with no manual input. We then assess the extent to which each sentiment measure, aggregated to monthly time series, can serve as a useful statistical indicator and forecast industrial production. Our results suggest that the text responses provide information beyond the available numerical data from the same survey and improve out-of-sample forecasting; deep learning methods and the use of naturally occurring labels seem especially useful for forecasting. We also explore what drives the predictions made by the deep learning models, and find that a relatively small number of words associated with very positive/negative sentiment account for much of the variation in the aggregatesentiment index.
- Open Access
- 1 March 2024
- Published by Board of Governors of the Federal Reserve System in Finance and Economics Discussion Series
- No. 2024-013,p. 1-28
In the Driver's Seat: Pandemic Fiscal Stimulus and Light Vehicles
This paper explores the impact of two fiscal programs, the Economic Impact Payments and the Paycheck Protection Program, on vehicle purchases and relates our findings to post-pandemic price pressures. We find that receiving a stimulus check increased the probability of purchasing new vehicles. In addition, the disbursement of funds from the Paycheck Protection Program was associated with a rise in local new car registrations. Our estimates indicate that these two programs account for a boost of 1 3/4 million units—or 12 percent—to new car sales in 2020. Furthermore, the induced boost in sales coincided with the presence of significant production constraints and exacerbated an inventory drawdown, thereby contributing to the rapid increase in new vehicle prices that prevailed in the subsequent years.
- 1 March 2024
- Published by Board of Governors of the Federal Reserve System in Finance and Economics Discussion Series
- No. 2024-013,p. 1-28
Open AccessIn the Driver's Seat: Pandemic Fiscal Stimulus and Light Vehicles
This paper explores the impact of two fiscal programs, the Economic Impact Payments and the Paycheck Protection Program, on vehicle purchases and relates our findings to post-pandemic price pressures. We find that receiving a stimulus check increased the probability of purchasing new vehicles. In addition, the disbursement of funds from the Paycheck Protection Program was associated with a rise in local new car registrations. Our estimates indicate that these two programs account for a boost of 1 3/4 million units—or 12 percent—to new car sales in 2020. Furthermore, the induced boost in sales coincided with the presence of significant production constraints and exacerbated an inventory drawdown, thereby contributing to the rapid increase in new vehicle prices that prevailed in the subsequent years.