Ensaios em macroeconomia: previsão macroeconômica, risco bancário e preferências do Banco Central
Autor(a) principal: | |
---|---|
Data de Publicação: | 2022 |
Tipo de documento: | Tese |
Idioma: | por |
Título da fonte: | Biblioteca Digital de Teses e Dissertações da UFPB |
Texto Completo: | https://repositorio.ufpb.br/jspui/handle/123456789/24759 |
Resumo: | The aim of the paper is to verify if the tone of the reports produced by the Central Bank of Brazil contain information that can be used to improve the precision of the projections of the macroeconomic indicators for a quarter ahead. Thus, we built predictors for inflation and GDP growth obtained from textual analyzes of the Copom Minutes and Inflation Report. For the creation of sentiment scores, we used a traditional fixed-lexicon dictionary approach and a new approach that uses machine learning to generate a time-varying dictionary. Next, we test the predictive power of the new variables for macroeconomic indicators for a period ahead. We also tested whether these new predictors are able to improve the performance of predictive models. The results show that the best predictions were obtained with the models that used the time-varying dictionary textual score series. The fact happened because this type of dictionary is capable of incorporating new terms that appear in the reports. We also found that market forecasts of average GDP growth can be improved with sentiment scores. But this was not verified for inflation. The main motivation of this paper is to use machine learning techniques to build a new insolvency risk rating metric for banks traded on B3. Then, a set of prediction models will be used to project the risk classification of these institutions. Conventionally, the literature analyzes the risk of bank insolvency based on accounting data and macroeconomic variables. In addition to these variables, this work will build a series of sentiment of the bank’s manager, via quarterly reports (ITR), and this will be used to improve the accuracy of bank risk forecasts. The results indicate that the banking risk classification, by the k-means algorithm, was able to classify 17% of the sample in the highest risk group (1), while 83% of the sample was in the lowest bankruptcy risk group (0). Using the Z-score metric, we found that 65% of the sample is part of the low-risk group and 35% of the sample is part of the high-risk group. Thus, the k-means algorithm is more rigorous in classifying a bank in the highest risk category. Next, we use the data already described to project the risk of bank insolvency. The results of this step showed that the decision tree model presented the best performance for the sample of test. In addition, it was found that the inclusion of the banking sentiment variable was able to improve the performance of forecast models, especially when banking sentiment is constructed from a time-varying dictionary. The objective of the paper is to investigate whether the Central Bank has been reacting to fiscal policy sentiment. The variable that measures the polarity of fiscal policy was constructed through natural language processing and sentiment analysis of monthly public debt reports issued by the National Treasury. The sentiment index was inserted as a dependent variable in two approaches to achieve the objective of the work. The first is the estimation of a traditional central bank reaction function. The second is the estimation of a DSGE model to estimate reaction functions and thus produce inferences about the effect of fiscal policy sentiment on monetary policy behavior. The main results suggest that fiscal policy sentiment has explicitly entered the monetary policy decision-making process in Brazil, indicating a possible scenario of fiscal dominance. |
id |
UFPB_8c02a05c9c091c3f51363eea1be7aa9c |
---|---|
oai_identifier_str |
oai:repositorio.ufpb.br:123456789/24759 |
network_acronym_str |
UFPB |
network_name_str |
Biblioteca Digital de Teses e Dissertações da UFPB |
repository_id_str |
|
spelling |
Ensaios em macroeconomia: previsão macroeconômica, risco bancário e preferências do Banco CentralPrevisão macroeconômicaMachine learningÍndice de sentimentoAta do copomRelatório da inflaçãoInsolvência bancáriaClusterSentimento bancárioAnálise de sentimentosFunção de reaçãoSentimento da política fiscalDSGEMacroeconomic forecastSentiment indexCopom minutesInflation reportBank insolvencyBanking sentimentSentiment analysisReaction functionSentiment of fiscal policyCNPQ::CIENCIAS SOCIAIS APLICADAS::ECONOMIAThe aim of the paper is to verify if the tone of the reports produced by the Central Bank of Brazil contain information that can be used to improve the precision of the projections of the macroeconomic indicators for a quarter ahead. Thus, we built predictors for inflation and GDP growth obtained from textual analyzes of the Copom Minutes and Inflation Report. For the creation of sentiment scores, we used a traditional fixed-lexicon dictionary approach and a new approach that uses machine learning to generate a time-varying dictionary. Next, we test the predictive power of the new variables for macroeconomic indicators for a period ahead. We also tested whether these new predictors are able to improve the performance of predictive models. The results show that the best predictions were obtained with the models that used the time-varying dictionary textual score series. The fact happened because this type of dictionary is capable of incorporating new terms that appear in the reports. We also found that market forecasts of average GDP growth can be improved with sentiment scores. But this was not verified for inflation. The main motivation of this paper is to use machine learning techniques to build a new insolvency risk rating metric for banks traded on B3. Then, a set of prediction models will be used to project the risk classification of these institutions. Conventionally, the literature analyzes the risk of bank insolvency based on accounting data and macroeconomic variables. In addition to these variables, this work will build a series of sentiment of the bank’s manager, via quarterly reports (ITR), and this will be used to improve the accuracy of bank risk forecasts. The results indicate that the banking risk classification, by the k-means algorithm, was able to classify 17% of the sample in the highest risk group (1), while 83% of the sample was in the lowest bankruptcy risk group (0). Using the Z-score metric, we found that 65% of the sample is part of the low-risk group and 35% of the sample is part of the high-risk group. Thus, the k-means algorithm is more rigorous in classifying a bank in the highest risk category. Next, we use the data already described to project the risk of bank insolvency. The results of this step showed that the decision tree model presented the best performance for the sample of test. In addition, it was found that the inclusion of the banking sentiment variable was able to improve the performance of forecast models, especially when banking sentiment is constructed from a time-varying dictionary. The objective of the paper is to investigate whether the Central Bank has been reacting to fiscal policy sentiment. The variable that measures the polarity of fiscal policy was constructed through natural language processing and sentiment analysis of monthly public debt reports issued by the National Treasury. The sentiment index was inserted as a dependent variable in two approaches to achieve the objective of the work. The first is the estimation of a traditional central bank reaction function. The second is the estimation of a DSGE model to estimate reaction functions and thus produce inferences about the effect of fiscal policy sentiment on monetary policy behavior. The main results suggest that fiscal policy sentiment has explicitly entered the monetary policy decision-making process in Brazil, indicating a possible scenario of fiscal dominance.Coordenação de Aperfeiçoamento de Pessoal de Nível Superior - CAPESO objetivo do artigo é verificar se o tom dos relatórios produzidos pelo Banco Central do Brasil contêm informações que podem ser utilizadas para melhorar a precisão das projeções dos indicadores macroeconômicos para um trimestre à frente. Assim, construímos preditores para a inflação e o crescimento do PIB obtidos a partir de análises textuais da Ata do Copom e do Relatório de Inflação. Para a criação dos índices de sentimento, usamos uma abordagem tradicional de dicionário de léxico fixo e uma nova abordagem que usa o aprendizado de máquina para gerar um dicionário variante no tempo. Em seguida, testamos o poder preditivo das novas variáveis para indicadores macroeconômicos para um período à frente. Também testamos se esses novos preditores são capazes de melhorar o desempenho dos modelos de previsão. Os resultados mostram que as melhores previsões foram obtidas com os modelos que utilizaram a série de pontuação textual de dicionário variante no tempo. O fato aconteceu porque esse tipo de dicionário é capaz de incorporar novos termos que aparecem nos relatórios. Também descobrimos que as previsões de crescimento médio do PIB do mercado podem ser melhoradas com índices de sentimento. Mas, isso não foi verificado para a inflação. A principal motivação deste artigo é utilizar técnicas de machine learning para construir uma nova métrica de classificação de risco de insolvência para os bancos negociados na B3. Em seguida, será utilizado um conjunto de modelos de predição para projetar a classificação de risco destas instituições. Convencionalmente, a literatura analisa o risco de insolvência bancária a partir dos dados contábeis e variáveis macroeconômicas. Além dessas variáveis, esse artigo irá construir uma série de sentimento do gestor da instituição bancária, via relatórios trimestrais (ITR), e essa será utilizada para melhorar a acurácia das previsões do risco bancário. Os resultados indicam que a classificação de risco bancário, via algoritmo k-means, foi capaz de classificar 17% da amostra no grupo de maior risco (1), enquanto 83% da amostra ficou no grupo de menor risco de falência (0). Utilizando a métrica do Z-score verificamos que 65% da amostra faz parte do grupo de baixo risco e 35% da amostra no grupo de risco elevado. Desse modo, o algoritmo k-means é mais rigoroso em classificar um banco na categoria de maior risco. Na sequência utilizamos os dados já descritos para projetar o risco de insolvência bancária. Os resultados desta etapa mostraram que o modelo de árvore de decisão apresentou o melhor desempenho para a amostra de teste. Além disso, constatou-se que a inclusão da variável de sentimento bancário foi capaz de melhorar o desempenho dos modelos de previsão, principalmente, quando o sentimento bancário é construído a partir de um dicionário variante no tempo. O objetivo do presente trabalho é investigar se o Banco Central vem reagindo ao sentimento da política fiscal. A variável que mede a polaridade da política fiscal foi construída por meio de processamento de linguagem natural e análise de sentimento dos relatórios mensais da dívida pública emitidos pelo Tesouro Nacional. O índice de sentimento foi inserido como variável dependente em duas abordagens para atingir o objetivo do artigo. A primeira é estimação de uma tradicional função de reação do banco central. A segunda é a estimação de um modelo DSGE para se estimar funções de reação e com isto produzir inferências sobre o efeito do sentimento da política fiscal no comportamento da política monetária. Os principais resultados sugerem que o sentimento da política fiscal tem entrado explicitamente no processo decisório da política monetária no Brasil, indicando um possível cenário de dominância fiscal.Universidade Federal da ParaíbaBrasilEconomiaPrograma de Pós-Graduação em EconomiaUFPBBesarria, Cássio da Nóbregahttp://lattes.cnpq.br/2341655229529160Jesus, Diego Pitta de2022-09-28T19:41:59Z2022-07-222022-09-28T19:41:59Z2022-02-25info:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/doctoralThesishttps://repositorio.ufpb.br/jspui/handle/123456789/24759porAttribution-NoDerivs 3.0 Brazilhttp://creativecommons.org/licenses/by-nd/3.0/br/info:eu-repo/semantics/openAccessreponame:Biblioteca Digital de Teses e Dissertações da UFPBinstname:Universidade Federal da Paraíba (UFPB)instacron:UFPB2022-10-25T12:58:12Zoai:repositorio.ufpb.br:123456789/24759Biblioteca Digital de Teses e Dissertaçõeshttps://repositorio.ufpb.br/PUBhttp://tede.biblioteca.ufpb.br:8080/oai/requestdiretoria@ufpb.br|| diretoria@ufpb.bropendoar:2022-10-25T12:58:12Biblioteca Digital de Teses e Dissertações da UFPB - Universidade Federal da Paraíba (UFPB)false |
dc.title.none.fl_str_mv |
Ensaios em macroeconomia: previsão macroeconômica, risco bancário e preferências do Banco Central |
title |
Ensaios em macroeconomia: previsão macroeconômica, risco bancário e preferências do Banco Central |
spellingShingle |
Ensaios em macroeconomia: previsão macroeconômica, risco bancário e preferências do Banco Central Jesus, Diego Pitta de Previsão macroeconômica Machine learning Índice de sentimento Ata do copom Relatório da inflação Insolvência bancária Cluster Sentimento bancário Análise de sentimentos Função de reação Sentimento da política fiscal DSGE Macroeconomic forecast Sentiment index Copom minutes Inflation report Bank insolvency Banking sentiment Sentiment analysis Reaction function Sentiment of fiscal policy CNPQ::CIENCIAS SOCIAIS APLICADAS::ECONOMIA |
title_short |
Ensaios em macroeconomia: previsão macroeconômica, risco bancário e preferências do Banco Central |
title_full |
Ensaios em macroeconomia: previsão macroeconômica, risco bancário e preferências do Banco Central |
title_fullStr |
Ensaios em macroeconomia: previsão macroeconômica, risco bancário e preferências do Banco Central |
title_full_unstemmed |
Ensaios em macroeconomia: previsão macroeconômica, risco bancário e preferências do Banco Central |
title_sort |
Ensaios em macroeconomia: previsão macroeconômica, risco bancário e preferências do Banco Central |
author |
Jesus, Diego Pitta de |
author_facet |
Jesus, Diego Pitta de |
author_role |
author |
dc.contributor.none.fl_str_mv |
Besarria, Cássio da Nóbrega http://lattes.cnpq.br/2341655229529160 |
dc.contributor.author.fl_str_mv |
Jesus, Diego Pitta de |
dc.subject.por.fl_str_mv |
Previsão macroeconômica Machine learning Índice de sentimento Ata do copom Relatório da inflação Insolvência bancária Cluster Sentimento bancário Análise de sentimentos Função de reação Sentimento da política fiscal DSGE Macroeconomic forecast Sentiment index Copom minutes Inflation report Bank insolvency Banking sentiment Sentiment analysis Reaction function Sentiment of fiscal policy CNPQ::CIENCIAS SOCIAIS APLICADAS::ECONOMIA |
topic |
Previsão macroeconômica Machine learning Índice de sentimento Ata do copom Relatório da inflação Insolvência bancária Cluster Sentimento bancário Análise de sentimentos Função de reação Sentimento da política fiscal DSGE Macroeconomic forecast Sentiment index Copom minutes Inflation report Bank insolvency Banking sentiment Sentiment analysis Reaction function Sentiment of fiscal policy CNPQ::CIENCIAS SOCIAIS APLICADAS::ECONOMIA |
description |
The aim of the paper is to verify if the tone of the reports produced by the Central Bank of Brazil contain information that can be used to improve the precision of the projections of the macroeconomic indicators for a quarter ahead. Thus, we built predictors for inflation and GDP growth obtained from textual analyzes of the Copom Minutes and Inflation Report. For the creation of sentiment scores, we used a traditional fixed-lexicon dictionary approach and a new approach that uses machine learning to generate a time-varying dictionary. Next, we test the predictive power of the new variables for macroeconomic indicators for a period ahead. We also tested whether these new predictors are able to improve the performance of predictive models. The results show that the best predictions were obtained with the models that used the time-varying dictionary textual score series. The fact happened because this type of dictionary is capable of incorporating new terms that appear in the reports. We also found that market forecasts of average GDP growth can be improved with sentiment scores. But this was not verified for inflation. The main motivation of this paper is to use machine learning techniques to build a new insolvency risk rating metric for banks traded on B3. Then, a set of prediction models will be used to project the risk classification of these institutions. Conventionally, the literature analyzes the risk of bank insolvency based on accounting data and macroeconomic variables. In addition to these variables, this work will build a series of sentiment of the bank’s manager, via quarterly reports (ITR), and this will be used to improve the accuracy of bank risk forecasts. The results indicate that the banking risk classification, by the k-means algorithm, was able to classify 17% of the sample in the highest risk group (1), while 83% of the sample was in the lowest bankruptcy risk group (0). Using the Z-score metric, we found that 65% of the sample is part of the low-risk group and 35% of the sample is part of the high-risk group. Thus, the k-means algorithm is more rigorous in classifying a bank in the highest risk category. Next, we use the data already described to project the risk of bank insolvency. The results of this step showed that the decision tree model presented the best performance for the sample of test. In addition, it was found that the inclusion of the banking sentiment variable was able to improve the performance of forecast models, especially when banking sentiment is constructed from a time-varying dictionary. The objective of the paper is to investigate whether the Central Bank has been reacting to fiscal policy sentiment. The variable that measures the polarity of fiscal policy was constructed through natural language processing and sentiment analysis of monthly public debt reports issued by the National Treasury. The sentiment index was inserted as a dependent variable in two approaches to achieve the objective of the work. The first is the estimation of a traditional central bank reaction function. The second is the estimation of a DSGE model to estimate reaction functions and thus produce inferences about the effect of fiscal policy sentiment on monetary policy behavior. The main results suggest that fiscal policy sentiment has explicitly entered the monetary policy decision-making process in Brazil, indicating a possible scenario of fiscal dominance. |
publishDate |
2022 |
dc.date.none.fl_str_mv |
2022-09-28T19:41:59Z 2022-07-22 2022-09-28T19:41:59Z 2022-02-25 |
dc.type.status.fl_str_mv |
info:eu-repo/semantics/publishedVersion |
dc.type.driver.fl_str_mv |
info:eu-repo/semantics/doctoralThesis |
format |
doctoralThesis |
status_str |
publishedVersion |
dc.identifier.uri.fl_str_mv |
https://repositorio.ufpb.br/jspui/handle/123456789/24759 |
url |
https://repositorio.ufpb.br/jspui/handle/123456789/24759 |
dc.language.iso.fl_str_mv |
por |
language |
por |
dc.rights.driver.fl_str_mv |
Attribution-NoDerivs 3.0 Brazil http://creativecommons.org/licenses/by-nd/3.0/br/ info:eu-repo/semantics/openAccess |
rights_invalid_str_mv |
Attribution-NoDerivs 3.0 Brazil http://creativecommons.org/licenses/by-nd/3.0/br/ |
eu_rights_str_mv |
openAccess |
dc.publisher.none.fl_str_mv |
Universidade Federal da Paraíba Brasil Economia Programa de Pós-Graduação em Economia UFPB |
publisher.none.fl_str_mv |
Universidade Federal da Paraíba Brasil Economia Programa de Pós-Graduação em Economia UFPB |
dc.source.none.fl_str_mv |
reponame:Biblioteca Digital de Teses e Dissertações da UFPB instname:Universidade Federal da Paraíba (UFPB) instacron:UFPB |
instname_str |
Universidade Federal da Paraíba (UFPB) |
instacron_str |
UFPB |
institution |
UFPB |
reponame_str |
Biblioteca Digital de Teses e Dissertações da UFPB |
collection |
Biblioteca Digital de Teses e Dissertações da UFPB |
repository.name.fl_str_mv |
Biblioteca Digital de Teses e Dissertações da UFPB - Universidade Federal da Paraíba (UFPB) |
repository.mail.fl_str_mv |
diretoria@ufpb.br|| diretoria@ufpb.br |
_version_ |
1801842999905222656 |