Forecasting indexes volatilities by using machine learning techniques, econometric and randomized models: A study on the forecasting capacity prediction of each model on the first days of the Ukraine’s Conflict

Detalhes bibliográficos
Autor(a) principal: Bettencourt, Francisco Gonçalves Cruces Matos
Data de Publicação: 2023
Tipo de documento: Dissertação
Idioma: eng
Título da fonte: Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos)
Texto Completo: http://hdl.handle.net/10362/149113
Resumo: Dissertation presented as the partial requirement for obtaining a Master's degree in Statistics and Information Management, specialization in Risk Analysis and Management
id RCAP_fd06821ecfa9494e2e45ff7089344922
oai_identifier_str oai:run.unl.pt:10362/149113
network_acronym_str RCAP
network_name_str Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos)
repository_id_str 7160
spelling Forecasting indexes volatilities by using machine learning techniques, econometric and randomized models: A study on the forecasting capacity prediction of each model on the first days of the Ukraine’s ConflictStock Volatility ForecastingMachine Learning Stock ForecastMonte Carlo StockGARCH Volatility ForecastLSTM StockDissertation presented as the partial requirement for obtaining a Master's degree in Statistics and Information Management, specialization in Risk Analysis and ManagementPredicting the volatility of returns for a stock index is an attractive and defying task in the field of Machine Learning (ML). The comparison of Machine Learning models, and their resulting predictions, with several Time Series algorithms and Monte Carlo simulations, could provide valuable insight regarding the advantage of using more recent Machine Learning methods to predict stock index volatility. In this article, a study is presented on the various models’ ability to predict for five worldwide Indexes, the returns and therefore, their volatilities, at the beginning of the Ukraine’s conflict. By applying and comparing the performance of different algorithms, this study aims to investigate if recent ML models could lead to enhanced predictive capabilities, when in comparison to more established and frequently used statical methods and/or random models. Therefore, as mentioned above, this study will be based on five indexes, namely the Euronext 100 (Europe), the National Stock Exchange India (India), the São Paulo Stock Exchange (South America), the NASDAQ (North America) and the Hang Seng Index (Hong Kong), and the data source will be the financial information, explained in detail in section 3, from January 1st 2015 until the March 4th 2022. The study and forecasting of volatility are of high value, since Pension/Investment funds, as well as other stakeholders in Financial Markets, recognize that the risk should be minimized to the maximum level, and be within the standards that Pension/Fund members agreed upon. With this being said, the main focus of this project will not be to try to obtain the most accurate model to predict the daily volatility, but to compare how different models said volatility and if their predictions fall very far from one another. The main finding of the study was that multivariable models had performed better than univariable and randomized models. Also, models that include data with different levels of frequency (daily, monthly, quarterly) have a better forecasting capacity.Damásio, Bruno Miguel PintoRUNBettencourt, Francisco Gonçalves Cruces Matos2023-02-13T18:38:16Z2023-01-242023-01-24T00:00:00Zinfo:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/masterThesisapplication/pdfhttp://hdl.handle.net/10362/149113TID:203221834enginfo:eu-repo/semantics/openAccessreponame:Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos)instname:Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informaçãoinstacron:RCAAP2024-03-11T05:30:51Zoai:run.unl.pt:10362/149113Portal AgregadorONGhttps://www.rcaap.pt/oai/openaireopendoar:71602024-03-20T03:53:37.188639Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) - Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informaçãofalse
dc.title.none.fl_str_mv Forecasting indexes volatilities by using machine learning techniques, econometric and randomized models: A study on the forecasting capacity prediction of each model on the first days of the Ukraine’s Conflict
title Forecasting indexes volatilities by using machine learning techniques, econometric and randomized models: A study on the forecasting capacity prediction of each model on the first days of the Ukraine’s Conflict
spellingShingle Forecasting indexes volatilities by using machine learning techniques, econometric and randomized models: A study on the forecasting capacity prediction of each model on the first days of the Ukraine’s Conflict
Bettencourt, Francisco Gonçalves Cruces Matos
Stock Volatility Forecasting
Machine Learning Stock Forecast
Monte Carlo Stock
GARCH Volatility Forecast
LSTM Stock
title_short Forecasting indexes volatilities by using machine learning techniques, econometric and randomized models: A study on the forecasting capacity prediction of each model on the first days of the Ukraine’s Conflict
title_full Forecasting indexes volatilities by using machine learning techniques, econometric and randomized models: A study on the forecasting capacity prediction of each model on the first days of the Ukraine’s Conflict
title_fullStr Forecasting indexes volatilities by using machine learning techniques, econometric and randomized models: A study on the forecasting capacity prediction of each model on the first days of the Ukraine’s Conflict
title_full_unstemmed Forecasting indexes volatilities by using machine learning techniques, econometric and randomized models: A study on the forecasting capacity prediction of each model on the first days of the Ukraine’s Conflict
title_sort Forecasting indexes volatilities by using machine learning techniques, econometric and randomized models: A study on the forecasting capacity prediction of each model on the first days of the Ukraine’s Conflict
author Bettencourt, Francisco Gonçalves Cruces Matos
author_facet Bettencourt, Francisco Gonçalves Cruces Matos
author_role author
dc.contributor.none.fl_str_mv Damásio, Bruno Miguel Pinto
RUN
dc.contributor.author.fl_str_mv Bettencourt, Francisco Gonçalves Cruces Matos
dc.subject.por.fl_str_mv Stock Volatility Forecasting
Machine Learning Stock Forecast
Monte Carlo Stock
GARCH Volatility Forecast
LSTM Stock
topic Stock Volatility Forecasting
Machine Learning Stock Forecast
Monte Carlo Stock
GARCH Volatility Forecast
LSTM Stock
description Dissertation presented as the partial requirement for obtaining a Master's degree in Statistics and Information Management, specialization in Risk Analysis and Management
publishDate 2023
dc.date.none.fl_str_mv 2023-02-13T18:38:16Z
2023-01-24
2023-01-24T00:00:00Z
dc.type.status.fl_str_mv info:eu-repo/semantics/publishedVersion
dc.type.driver.fl_str_mv info:eu-repo/semantics/masterThesis
format masterThesis
status_str publishedVersion
dc.identifier.uri.fl_str_mv http://hdl.handle.net/10362/149113
TID:203221834
url http://hdl.handle.net/10362/149113
identifier_str_mv TID:203221834
dc.language.iso.fl_str_mv eng
language eng
dc.rights.driver.fl_str_mv info:eu-repo/semantics/openAccess
eu_rights_str_mv openAccess
dc.format.none.fl_str_mv application/pdf
dc.source.none.fl_str_mv reponame:Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos)
instname:Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informação
instacron:RCAAP
instname_str Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informação
instacron_str RCAAP
institution RCAAP
reponame_str Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos)
collection Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos)
repository.name.fl_str_mv Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) - Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informação
repository.mail.fl_str_mv
_version_ 1799138126598242304

Registros relacionados