Bàrbara Llacay
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Bàrbara Llacay has a total of 10 co-authors. Here are the top co-authors by number of shared publications:
Gilbert Peffer
Centre Internacional de Mètodes Numèrics en Enginyeria (CIMNE) Barcelona Spain
6 shared publicationsB Koppe
1 shared publication- David Alaminos
Department of Business, University of Barcelona, Barcelona, Spain
1 shared publication G Peffer
1 shared publication- Gilbert Peffer
CIMNE-University of Barcelona
1 shared publication - Gilbert Peffer
Kubify Utrecht Netherlands
1 shared publication
Latest Publications
- Open Access
- 15 May 2026
- Published by Elsevier in Finance Research Letters
- Vol. 104
From value-at-risk to expected shortfall: An agent-based analysis of market stability
- 15 May 2026
- Published by Elsevier in Finance Research Letters
- Vol. 104
Open AccessFrom value-at-risk to expected shortfall: An agent-based analysis of market stability
- Open Access
- 9 September 2024
- Published by Walter de Gruyter GmbH
- p. 203-224
Chapter 15 Forecasting Brent Oil Volatility: DeepAR vs LSTM
The recent international crises have revealed the economy’s vulnerability to fluctuations in commodity prices. Expectations on the volatility of the current price mark strategic decisions of companies and investors, especially in the case of oil. Given its importance, modelling with computational techniques has intensified in recent years. This study models the prediction of Brent oil volatility with Deep Autoregressive Recurrent Networks (DeepAR), an algorithm drawing from traditional autoregressive models. Our results demonstrate an improvement in the classification results and error levels with the DeepAR after comparing to Long Short-Term Memory (LSTM) and previous similar works, with a level range of 0.0007-0.0057 in root mean squared error (RMSE) terms. The application of the methodology offers a new alternative in volatility prediction to different interest groups, such as companies, institutional and individual investors and public institutions, as well as the possibility of broadening its applicability to the volatility of other assets.
- 9 September 2024
- Published by Walter de Gruyter GmbH
- p. 203-224
Open AccessChapter 15 Forecasting Brent Oil Volatility: DeepAR vs LSTM
The recent international crises have revealed the economy’s vulnerability to fluctuations in commodity prices. Expectations on the volatility of the current price mark strategic decisions of companies and investors, especially in the case of oil. Given its importance, modelling with computational techniques has intensified in recent years. This study models the prediction of Brent oil volatility with Deep Autoregressive Recurrent Networks (DeepAR), an algorithm drawing from traditional autoregressive models. Our results demonstrate an improvement in the classification results and error levels with the DeepAR after comparing to Long Short-Term Memory (LSTM) and previous similar works, with a level range of 0.0007-0.0057 in root mean squared error (RMSE) terms. The application of the methodology offers a new alternative in volatility prediction to different interest groups, such as companies, institutional and individual investors and public institutions, as well as the possibility of broadening its applicability to the volatility of other assets.
- Open Access
Market Impact Analysis of Financial Literacy among A-Share Market Investors: An Agent-Based Model
Financial literacy has become increasingly crucial in today’s complex financial markets. This paper explores the impact of financial literacy on the stock market by establishing an artificial financial market that aligns with the characteristics of the Chinese A-share market using agent-based modeling. The study incorporates financial literacy into investors’ mixed beliefs and simulates their behavior in the market. The results show that improving individual investors’ financial literacy can improve market quality and investor performance, as well as reduce the unequal distribution of wealth to some extent. However, the phenomenon of speculative trading and irrational behavior in the market can pose potential risks that require regulatory measures. Thus, policy recommendations to improve individual investors’ financial literacy and establish corresponding regulatory measures are proposed.
Open AccessMarket Impact Analysis of Financial Literacy among A-Share Market Investors: An Agent-Based Model
Financial literacy has become increasingly crucial in today’s complex financial markets. This paper explores the impact of financial literacy on the stock market by establishing an artificial financial market that aligns with the characteristics of the Chinese A-share market using agent-based modeling. The study incorporates financial literacy into investors’ mixed beliefs and simulates their behavior in the market. The results show that improving individual investors’ financial literacy can improve market quality and investor performance, as well as reduce the unequal distribution of wealth to some extent. However, the phenomenon of speculative trading and irrational behavior in the market can pose potential risks that require regulatory measures. Thus, policy recommendations to improve individual investors’ financial literacy and establish corresponding regulatory measures are proposed.
- Open Access
- 23 May 2023
- Published by Wiley in Expert Systems
- Vol. 42 (1)
Categorical surrogation of agent‐based models: A comparative study of machine learning classifiers
Agent‐based modelling has gained recognition in the last years because it provides a natural way to explore the behaviour of social systems. However, agent‐based models usually have a considerable number of parameters that make it computationally prohibitive to explore the complete space of parameter combinations. A promising approach to overcome the computational constraints of agent‐based models is the use of machine learning‐based surrogates or metamodels, which can be used as efficient proxies of the original agent‐based model. As the use of metamodels of agent‐based simulations is still an incipient area of research, there are no guidelines on which algorithms are the most suitable candidates. In order to contribute to filling this gap, we conduct here a systematic comparative analysis to evaluate different machine learning‐based approaches to agent‐based model surrogation. A key innovation of our work is the focus on classification methods for categorical metamodeling, which is highly relevant because agent‐based simulations are very often validated in a qualitative way. To analyse the performance of the classifiers we use three types of indicators—measures of correctness, efficiency, and robustness—and compare their results for different datasets and sample sizes using an agent‐based artificial market as a case study.
- 23 May 2023
- Published by Wiley in Expert Systems
- Vol. 42 (1)
Open AccessCategorical surrogation of agent‐based models: A comparative study of machine learning classifiers
Agent‐based modelling has gained recognition in the last years because it provides a natural way to explore the behaviour of social systems. However, agent‐based models usually have a considerable number of parameters that make it computationally prohibitive to explore the complete space of parameter combinations. A promising approach to overcome the computational constraints of agent‐based models is the use of machine learning‐based surrogates or metamodels, which can be used as efficient proxies of the original agent‐based model. As the use of metamodels of agent‐based simulations is still an incipient area of research, there are no guidelines on which algorithms are the most suitable candidates. In order to contribute to filling this gap, we conduct here a systematic comparative analysis to evaluate different machine learning‐based approaches to agent‐based model surrogation. A key innovation of our work is the focus on classification methods for categorical metamodeling, which is highly relevant because agent‐based simulations are very often validated in a qualitative way. To analyse the performance of the classifiers we use three types of indicators—measures of correctness, efficiency, and robustness—and compare their results for different datasets and sample sizes using an agent‐based artificial market as a case study.
- 26 December 2019
- Published by SAGE Publications in Algorithmic Finance
- Vol. 8 (1-2) , 5-26
Impact of short-sales in stock market efficiency
In the last two decades, the hedge fund sector has experienced a spectacular growth, up to the point that it is currently estimated to move more than 50% of the daily volume of stock markets. In contrast to other financial institutions, hedge funds
- 26 December 2019
- Published by SAGE Publications in Algorithmic Finance
- Vol. 8 (1-2) , 5-26
Impact of short-sales in stock market efficiency
In the last two decades, the hedge fund sector has experienced a spectacular growth, up to the point that it is currently estimated to move more than 50% of the daily volume of stock markets. In contrast to other financial institutions, hedge funds
- Open Access
- 1 January 2019
- Published by Journal of Artificial Societies and Social Simulation in Journal of Artificial Societies and Social Simulation
- Vol. 22 (1)
Impact of Basel III Countercyclical Measures on Financial Stability: An Agent-Based Model
- 1 January 2019
- Published by Journal of Artificial Societies and Social Simulation in Journal of Artificial Societies and Social Simulation
- Vol. 22 (1)
Open AccessImpact of Basel III Countercyclical Measures on Financial Stability: An Agent-Based Model
- 1 September 2017
- Published by Elsevier in Journal of Economic Dynamics and Control
- Vol. 82, 223-256
Impact of value-at-risk models on market stability
- 1 September 2017
- Published by Elsevier in Journal of Economic Dynamics and Control
- Vol. 82, 223-256
Impact of value-at-risk models on market stability
- Open Access
- 29 August 2017
- Published by Springer Nature in Computational and Mathematical Organization Theory
- Vol. 24 (3) , 308-350
Using realistic trading strategies in an agent-based stock market model
- 29 August 2017
- Published by Springer Nature in Computational and Mathematical Organization Theory
- Vol. 24 (3) , 308-350
Open AccessUsing realistic trading strategies in an agent-based stock market model
- 1 June 2010
- Published by World Scientific Pub Co Pte Ltd
- p. 189-196
REALISTIC AGENT-BASED SIMULATION OF FINANCIAL CRISES: THE 1998 TURMOIL
- 1 June 2010
- Published by World Scientific Pub Co Pte Ltd
- p. 189-196
REALISTIC AGENT-BASED SIMULATION OF FINANCIAL CRISES: THE 1998 TURMOIL
- 1 August 2009
- Published by Springer Nature
- p. 129-144
Foundations for a Framework for Multiagent-Based Simulation of Macrohistorical Episodes in Financial Markets
- 1 August 2009
- Published by Springer Nature
- p. 129-144
Foundations for a Framework for Multiagent-Based Simulation of Macrohistorical Episodes in Financial Markets