Sebastiano Manzan's research while affiliated with City University of New York - Bernard M. Baruch College and other places

Publications (46)

Article
Full-text available
Extracting sentiment from news text, social media and blogs has recently gained increasing interest in economics and finance. Despite many successful applications of sentiment analysis (SA) in these domains, the range of semantic techniques employed is still limited and predominantly focused on the detection of sentiment at a coarse-grained level....
Article
Full-text available
The goal of this paper is to evaluate the informational content of sentiment extracted from news articles about the state of the economy. We propose a fine-grained aspect-based sentiment analysis that has two main characteristics: 1) we consider only the text in the article that is semantically dependent on a term of interest (aspect-based) and, 2)...
Conference Paper
Full-text available
Lexicon-based Sentiment Analysis relies on sentiment dictionaries which are used to assign a sentiment polarity to the words of an input text. The overall sentiment of the text is then computed by means of a combining function, such as the word count, sum or average. In this short contribution we describe a detailed set of linguistic rules that all...
Technical Report
Full-text available
Modern economies produce massive datasets that need to be analysed using new modelling techniques like those from data science. The exploration of such huge and real-time amount of information generates new insights that are potentially useful for policymakers when designing policy interventions. The second edition of the Big Data and Economic Fore...
Article
Full-text available
We use a dataset of 12 million residential mortgages to investigate the loan default behavior in several European countries. We model the default occurrence as a function of borrower characteristics, loan-specific variables, and local economic conditions. We compare the performance of a set of machine learning algorithms relative to the logistic re...
Chapter
Full-text available
This chapter is an introduction to the use of data science technologies in the fields of economics and finance. The recent explosion in computation and information technology in the past decade has made available vast amounts of data in various domains, which has been referred to as Big Data . In economics and finance, in particular, tapping into t...
Chapter
Full-text available
Forecasting economic and financial variables is a challenging task for several reasons, such as the low signal-to-noise ratio, regime changes, and the effect of volatility among others. A recent trend is to extract information from news as an additional source to forecast economic activity and financial variables. The goal is to evaluate if news ca...
Article
I investigate how professional forecasters update their uncertainty forecasts of output and inflation in response to macroeconomic news. I obtain a measure of individual uncertainty from the density forecasts of the Survey of Professional Forecasters for the United States (US-SPF) and the Euro area (ECB-SPF) and use it to test the prediction of Bay...
Preprint
The goal of this paper is to evaluate the informational content of sentiment extracted from news articles about the state of the economy. We propose a Fine-Grained Aspect-based Sentiment analysis that has two main characteristics: 1) we consider only the text in the article that is semantically dependent on a term of interest (aspect-based) and, 2)...
Book
Full-text available
This document presents the contributions discussed at the second institutional workshop on Artificial Intelligence (AI), organized by the Joint Research Centre (JRC) of the European Commission. This workshop was held on 05th July 2019 at the premises of the JRC in Ispra (Italy), with video-conference to all JRC's sites. The workshop aimed to gather...
Technical Report
Full-text available
The JRC's Centre for Advanced Studies (CAS) was created in 2016 to help improve and bridge the interface between science and policy in order to enhance the JRC's capacity to better inform and influence the regulatory frameworks needed to address the new and emerging societal challenges confronting the EU and our societies as a whole. By creating t...
Chapter
We provide an overview on the development of a fine-grained, aspect-based sentiment analysis approach aimed at providing useful signals to improve forecasts of economic models and produce more accurate predictions. The approach is unsupervised since it relies on external lexical resources to associate a polarity score to a given term or concept. Af...
Article
The aim of this paper is to investigate the evidence of time-variation and asymmetry in the persistence of U.S. inflation. We evaluate these features by comparing the out-of-sample forecast performance of two specifications, a Quantile Auto-Regressive (QAR) model and a parametric Auto-Regressive (AR) model in which the volatility of the errors depe...
Article
In this paper we investigate the relevance of considering a large number of macroeconomic indicators to forecast the complete distribution of a variable. The baseline time series model is a semi-parametric specification based on the Quantile Auto-Regressive (QAR) model that assumes that the quantiles depend on the lagged values of the variable. We...
Article
The aim of this paper is to forecast (out-of-sample) the distribution of financial returns based on realized volatility measures constructed from high-frequency returns. We adopt a semi-parametric model for the distribution by assuming that the return quantiles depend on the realized measures and evaluate the distribution, quantile and interval for...
Article
The impact of offshoring on average labor productivity is investigated on a panel of 17 manufacturing sectors between 1989-2006. As proxies for offshoring, we use imports and import penetration, defined as the ratio of imports to output. We disaggregate the universe of exporters into low wage countries, NAFTA and the rest of the world. Controlling...
Article
The evaluation of the impact of an increase in gasoline tax on demand relies crucially on the estimate of the price elasticity. This article presents an extended application of the Partially Linear Additive Model (PLAM) to the analysis of gasoline demand using a panel of U.S. households, focusing mainly on the estimation of the price elasticity. Un...
Article
In this paper we estimate a simple Bayesian learning model to expectations data from the Survey of Professional Forecasters. We reformulate the model in terms of forecast revisions, which allows to abstract from differences in priors and to focus the analysis on the relationship between revisions and signal. The model depends on two parameters, the...
Article
Glossary Definition of the Subject Introduction The Standard RE Model Analytical Agent-Based Models Computational Agent-Based Models Other Applications in Finance Future Directions Bibliography
Article
I study the dynamics of oil futures prices in the NYMEX using a large panel dataset that includes global macroeconomic indicators, financial market indices, quantities and prices of energy products. I extract common factors from the panel data series and estimate a Factor-Augmented Vector Autoregression for the maturity structure of oil futures pri...
Article
Interest in density forecasts (as opposed to solely modeling the conditional mean) arises from the possibility of dynamics in higher moments of a time series, as well as in forecasting the probability of future events in some applications. By combining the idea of Markov bootstrapping with that of kernel density estimation, this paper presents a si...
Article
The evaluation of the impact of an increase in gasoline tax on demand relies crucially on the estimate of the price elasticity. This paper presents an extended application of the Partially Linear Additive Model (PLAM) to the analysis of gasoline demand using a panel of US households, focusing mainly on the estimation of the price elasticity. Unlike...
Article
Tolls are frequently discussed policies to reduce traffic in cities. However, road pricing measures are seldom implemented due to high investments and unpopularity. Transportation planning tools can support planning authorities by solving those problems if they take into account the following aspects: - Demographic attributes like income and time c...
Article
Forecasts are an inherent part of economic science and the quest for perfect foresight occupies economists and researchers in multiple fields. The release of economic forecasts (and its revisions) is a popular and often publicized event, with a multitude of institutions and think-tanks devoted almost exclusively to that task. The European Central B...
Article
This short paper is a comment on “Univariate tests for nonlinear structure” by Catherine Kyrtsou and Apostolos Serletis. We summarize their main results and discuss some of their conclusions concerning the role of outliers and noisy chaos. In particular, we include some new simulations to investigate whether economic time series may be characterize...
Article
Guided by psychological evidence, we develop a behavioral exchange rate model in which investors’ perception of fundamental shocks switches between two states. According to the representativeness heuristic, agents underestimate the informational content of news in calm periods, whereas they overreact to news if they encounter a series of distinct e...
Article
In this paper, we introduce a kernel estimator for the finite-dimensional parameter of a partially linear additive model. Under some regularity conditions, we establish n1/2-consistency and asymptotic normality of the estimator. Unlike existing kernel-based estimators: Fan et al. (1998. Ann. Statist. 26, 943-971) and Fan and Li (2003. Statist. Sini...
Article
This paper makes two contribution to the literature on density forecasts. First, we propose a novel bootstrap approach to estimate forecasting densities based on nonparametric techniques. The method is based on the Markov Bootstrap that is suitable to resample dependent data. The combination of nonparametric and bootstrap methods delivers density f...
Article
We investigate the finite-sample performance of model selection criteria for local linear regression by simulation. Similarly to linear regression, the penalization term depends on the number of parameters of the model. In the context of nonparametric regression, we use a suitable quantity to account for the Equivalent Number of Parameters as previ...
Article
Full-text available
We re-examine the relationship between exchange rates and order flow as proposed by Evans and Lyons (2002). Compared to their linear specification, we find that the response of exchange rates to order flow may depend on market historical volatility. If market historical volatility is high, a given order seems to have a lower price impact than in ca...
Article
Full-text available
We propose information theoretic tests for serial independence and linearity in time series against nonlinear dependence on lagged variables, based on the conditional mutual information. The conditional mutual information, which is a general measure for dependence, is estimated using the correlation integral from chaos theory. The significance of t...
Article
Full-text available
We investigate the determinants of forecast heterogeneity in the JPY/USD market using panel data from Consensus Economics. We find that past exchange-rate volatility increases forecast dispersion, while foreign exchange intervention of the Japanese Ministry of Finance dampens expectation heterogeneity.
Article
Full-text available
We investigate the determinants of forecast heterogeneity in the JPY/USD market using panel data from Consensus Economics. We find that past exchange-rate volatility increases forecast dispersion, while foreign exchange intervention of the Japanese Ministry of Finance dampens expectation heterogeneity.

Citations

... For example, we extract sentences from news that involve concepts such as employment, layoffs, industrial production, and house prices, among many others. Within each sentence, we then examine the semantic dependence to identify the adverbs, verbs, and adjectives that are used as modifiers of the economic concepts (similar approach to Consoli et al., 2022;Gardner et al., 2022). ...
... This information can be used to enrich and sharpen economic analysis [8], as in the case of the application of sentiment analysis to forecast economic and financial variables. In particular, sentiment derived from news is especially useful when forecasting macroeconomic variables, since it allows the state of the economy to be monitored in real-time, as opposed to the official releases of macroeconomic variables that are seldom available and with significant delays [4,9,10]. ...
... Central banks publish their flash estimates towards the end of the quarter. Economic sentiment data can then be used to nowcast the GDP growth data, as in Barbaglia et al. (2021). Another application is the monitoring of government popularity. ...
... In line with this study, COVID-19 pandemic led to economic recession which would exacerbate household credit risk and vulnerability. Despite macroeconomic factor, household characteristics could be as the determinant of NPL, for instance, debt to asset, debt to income, occupation, age, and gender (Albacete and Linder, * The results and opinions expressed in this paper are the authors' own and do not necessarily represent those of the Central Bank of Indonesia 2013; Deng and Liu, 2008;Shi et al., 2013;Alvaro and Gallardo, 2012;Feng et al., 2018;Jadhav et al., 2018;Barbaglia et al., 2020). ...
... Although employing ML techniques for decision making, and by extension for StatArb, seems to be the best viable option, practitioners require to understand how the employed ML models undertake their decisions. Often referred to as "black boxes", ML models are developed with a single goal of maximizing predictive performance (Barbaglia et al., 2021). The European GDPR regulation (Goddard, 2017) states that the existence of automated decision-making should carry meaningful information about the logic involved, as well as the significance and the envisaged consequences of such processing for the data subject. ...
... The resulting score is a floating point value in the range between −1 (extremely negative/bearish) and +1 (extremely positive/bullish), with 0 representing a neutral sentiment. The FiGAS sentiment score has two characteristics [38]. Firstly, it is based on a fine-grained dictionary that has been specifically developed for applications in the economic and financial domain. ...
... Measuring the informational content of text in economic and financial news is useful for market participants to adjust their perception and expectations on the dynamics of financial markets. In this context, the incorporation in forecasting models of economic and financial information coming from news media has already demonstrated great potentials [1][2][3]5]. Our endeavour is to study the predictive power of news for forecasting financial variables by leveraging on the recent advances in word embeddings [9,21] and deep learning [17,24] models. ...
... A new lower bin was then added for the 2009:Q2 survey, '< −3', and the aggregate histogram indicated a 24% chance of this event. However, as was noted by Manzan (2016), there are no other quarters in which a large average probability is assigned to an open interval, so that any distortionary effects are likely to be minor (and will have no effect on the Q3 and Q4 survey forecasts). However, Manzan (2016) shows that the problem is more acute for the European Central Bank SPF, and suggests the fitting of 'artificial' triangular distributions, based on the assumption that an individual's point prediction can be regarded as an estimate of the mode of his/her underlying distribution. ...
... We extract sentences referring to specific economic and financial aspects, by using a keyword-based information extraction procedure with search keywords broadly related to the Spanish economy, monetary and fiscal policies. 6 In order to filter out only sentences referring to Spain, we also use a location detection heuristic [1] assigning the location to which a sentence is referring as its most frequent named-entity location detected in the news text, and then selecting only sentences with specific assigned location labels related to Spain. With this procedure we obtain a total of over 4.2 million sentences. ...
... Machine learning techniques have been shown to outperform established approaches in predicting various other time series, such as stock-level expected returns (e.g., Gu et al., 2020, and Leippold et al., 2021, bond risk premia (e.g., Bianchi et al., 2021), and loan defaults (e.g., Barbaglia et al., 2021). Realized betas are less noisy than realized returns. ...