Research
PUBLICATIONS
A New Supply Bottlenecks Index Based on Newspaper Data International Journal of Central Banking (2024), volume 20, number 2, pp. 17-67. With Pablo Burriel, Iván Kataryniuk and Francesca Viani. Data available here.
Also: Documentos de Trabajo N.º 2304 Banco de España.
We develop a new monthly indicator of supply bottlenecks using newspaper articles. The supply bottlenecks index (SBI) provides a consistent narrative of supply issues related to wars, natural disasters, strikes and, most recently, the COVID-19 pandemic. Innovations in the SBI have important macroeconomic implications: an increase in the SBI functions as a cost-push shock, decreasing industrial production and employment, and pushing prices up, so that monetary policy faces important trade-offs.
Natural Language Processing and Financial Markets: Semi-Supervised Modelling of Coronavirus and Economic News - Advances in Data Analysis and Classification (ADAC) (2024). With Marco Minozzo.
Also: Documentos de Trabajo N.º 2228 Banco de España. Also: SUERF Policy Brief.
This paper investigates the reactions of US financial markets to press news from January 2019 to 1 May 2020. To this end, we deduce the content and uncertainty of the news by developing apposite indices from the headlines and snippets of The New York Times, using unsupervised machine learning techniques. In particular, we use Latent Dirichlet Allocation to infer the content (topics) of the articles, and Word Embedding (implemented with the Skip-gram model) and K-Means to measure their uncertainty. In this way, we arrive at the definition of a set of daily topic-specific uncertainty indices. These indices are then used to find explanations for the behavior of the US financial markets by implementing a batch of EGARCH models. In substance, we find that two topic-specific uncertainty indices, one related to COVID-19 news and the other to trade war news, explain the bulk of the movements in the financial markets from the beginning of 2019 to end-April 2020. Moreover, we find that the topic-specific uncertainty index related to the economy and the Federal Reserve is positively related to the financial markets, meaning that our index is able to capture the actions of the Federal Reserve during periods of uncertainty.
Presented at the conference ‘Modelling with Big Data & Machine Learning: Measuring Economic Instability’. The Bank of England, the Federal Reserve Board and King’s College. (slides)
‘Making Text Talk’: The Minutes of the Central Bank of Brazil and the Real Economy - Forthcoming: Journal of International Money and Finance. With Marco Minozzo.
Also: Documentos de Trabajo N.º 2240 Banco de España.
This paper investigates the relationship between the views expressed in the minutes of the meetings of the Central Bank of Brazil’s Monetary Policy Committee (COPOM) and the real economy. It applies various computational linguistic machine learning algorithms to construct measures of the minutes of the COPOM. First, we infer the content of the paragraphs of the minutes with Latent Dirichlet Allocation. Second, we build an uncertainty index for the minutes with Word Embeddings and K-Means. Then, we create two topic-uncertainty indices. The first topic-uncertainty index is constructed from paragraphs with a higher probability of topics related to ‘general economic conditions’. A second topic-uncertainty index is constructed from paragraphs that have a higher probability of topics related to ‘inflation’ and the ‘monetary policy discussion’. Finally, via a Structural VAR we explore the lasting effects of these uncertainty indices on some Brazilian macroeconomic variables. Our results show that greater uncertainty leads to a decline in inflation, the exchange rate, industrial production and the retail trade in the period from 2000 to July 2019.
PUBLICATIONS IN SPANISH
The Next Generation EU program: features and keys to success (2022) (In Spanish). ICE Revista de Economía, núm 924. With Daniel Alonso, Iván Kataryniuk and Javier J. Pérez.
The Next Generation EU program is designed to enhance potential growth, contribute towards the reductions of gaps between the European economies, and to mitigate, temporarily, two shortcomings in the European institutional framework (the lack of supranational stabilizing fiscal elements and the scarcity of safe assets). However, the final impact of the program is uncertain, and will depend crucially on the ability to allocate and implement in a transparent way the different projects.
WORKING PAPERS
Monetary Policy Uncertainty in Mexico: An Unsupervised Approach - Documentos de Trabajo N.º 2229 Banco de España. With Marco Minozzo.
We study and measure uncertainty in the minutes of the meetings of the board of governors of the Bank of Mexico and relate it to monetary policy variables. In particular, we conceive two uncertainty indices for the Spanish version of the minutes using unsupervised machine learning techniques. The first uncertainty index is constructed exploiting Latent Dirichlet Allocation (LDA), whereas the second uses the Skip-Gram model and K-Means. We also create uncertainty indices for the three main sections of the minutes. We find that higher uncertainty in the minutes is related to an increase in inflation and money supply. Our results also show that a unit shock in uncertainty leads to changes of the same sign but different magnitude of the inter-bank interest rate and the target interest rate. We also find that a unit shock in uncertainty leads to a depreciation of the Mexican peso with respect to the US dollar in the same period of the shock, which is followed by appreciation in the subsequent period.
Presentation at the conference ‘2020 Banca d’Italia and Federal Reserve Board Joint Conference on Nontraditional Data & Statistical Learning with Applications to Macroeconomics’. Banca d’Italia and the Federal Reserve Board. (slides)
POLICY PAPERS
Fiscal Policy Measures Adopted since the Second Wave of the Health Crisis: the Euro Area, the United States and the United Kingdom (2021). Documentos Ocasionales number 2118 Banco de España. With Daniel Alonso, Alejandro Buesa, Susana Párraga and Francesca Viani.
The persistence of the health crisis made it necessary for the main advanced economies to approve fresh fiscal measures or extend the terms of those that expired. This paper summarises the main actions taken since autumn 2020 in the main euro area economies (Germany, France, Italy and Spain), the United States and the United Kingdom, supplementing a previous paper (Cuadro-Sáez et al. (2020)) that focused on the measures approved in the first half of 2020. Also, the actions taken within the State aid temporary framework, adopted by the European Commission to provide direct support to the most affected firms and to limit trade and competition distortions in the internal market, are detailed. This set of actions has helped to mitigate the risks associated with an early withdrawal of fiscal stimulus. Notable among the new measures adopted is the additional support for firms in European countries, the direct assistance to households in the United States and the new employment support provisions in the United Kingdom.
Fiscal Policy Response to the Crisis in the Euro Area and the United States (2020). Box 2 Economic bulletin [4/2020] Banco de España. With Luis Guirola and Iván Kataryniuk.