Forecasting of corporate revenues with machine learning models versus traditional methods in the digital industry
Autor(a) principal: | |
---|---|
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/10400.14/42245 |
Resumo: | There has been a growing interest in the applicability of machine learning models in corporate sales and revenues forecasting. Past research has found promising results in this field, which show that these models might outperform more traditional methods. In this thesis, three real-world datasets containing information about the revenues and other fea tures of Amazon, Microsoft and Netflix in the last two decades are investigated to forecast the revenues of these digital companies. Firstly, we apply different pre-processing tech niques on the data, which include seasonal differencing using logarithm transformations. Then, some more classical time-series methods including Autoregressive model or order 1 are built. Moreover, different machine learning models including Partial Least Squares and Deep Neural network are applied. Finally, an empirical comparison of the models is performed using metrics such as Mean Absolute Error and Akaike Information Criterion. The results show that Autoregressive model of order 1 outperforms all the other models in terms of revenues forecasting accuracy in all datasets. Particularly, comparing with the benchmark machine learning model in each dataset, this method is able to reduce the error by more than 12 % and up to 72 %. Although these findings require further research to ad dress any possible limitations, they provide insights on the performance of several models in revenues forecasting of digital firms, which can be a valuable tool for the decision-making process of businesses in this industry. |
id |
RCAP_196343348c93053357c69e1b35586152 |
---|---|
oai_identifier_str |
oai:repositorio.ucp.pt:10400.14/42245 |
network_acronym_str |
RCAP |
network_name_str |
Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) |
repository_id_str |
7160 |
spelling |
Forecasting of corporate revenues with machine learning models versus traditional methods in the digital industryMachine learningSales and revenues forecastingDigital companiesPre-processingTime seriesEmpirical comparisonAccuracyMachine learningPrevisão de vendas e receitasPre-processamentoSéries temporaisComparaçãoEmpresas digitaisDomínio/Área Científica::Ciências Sociais::Economia e GestãoThere has been a growing interest in the applicability of machine learning models in corporate sales and revenues forecasting. Past research has found promising results in this field, which show that these models might outperform more traditional methods. In this thesis, three real-world datasets containing information about the revenues and other fea tures of Amazon, Microsoft and Netflix in the last two decades are investigated to forecast the revenues of these digital companies. Firstly, we apply different pre-processing tech niques on the data, which include seasonal differencing using logarithm transformations. Then, some more classical time-series methods including Autoregressive model or order 1 are built. Moreover, different machine learning models including Partial Least Squares and Deep Neural network are applied. Finally, an empirical comparison of the models is performed using metrics such as Mean Absolute Error and Akaike Information Criterion. The results show that Autoregressive model of order 1 outperforms all the other models in terms of revenues forecasting accuracy in all datasets. Particularly, comparing with the benchmark machine learning model in each dataset, this method is able to reduce the error by more than 12 % and up to 72 %. Although these findings require further research to ad dress any possible limitations, they provide insights on the performance of several models in revenues forecasting of digital firms, which can be a valuable tool for the decision-making process of businesses in this industry.Tem havido um interesse crescente no uso de modelos de machine learning para a pre visao de vendas e receitas das empresas. Pesquisas recentes revelaram resultados promis- ˜ sores, que mostram que estes modelos podem superar metodos de previs ´ ao mais cl ˜ assicos. ´ Nesta tese, sao investigadas tr ˜ es bases de dados que cont ˆ em informac¸ ˆ ao sobre as receitas ˜ e outros atributos das empresas Amazon, Microsoft e Netflix nas ultimas duas d ´ ecadas, ´ com o objetivo de prever as suas receitas. Comec¸amos por aplicar diversas tecnicas de ´ pre-processamento dos dados, que incluem as diferenc¸as hom ´ ologas de logaritmos. Pos- ´ teriormente, sao implementados alguns m ˜ etodos mais cl ´ assicos de previs ´ ao de s ˜ eries tem- ´ porais como o modelo autorregressivo de ordem 1. Sao desenvolvidos tamb ˜ em diferentes ´ modelos de machine learning como o modelo dos m´ınimos quadrados parciais e redes neu ronais. Por fim, e feita uma comparac¸ ´ ao dos modelos, utilizando diferentes m ˜ etricas como ´ o erro medio absoluto e o crit ´ erio de informac¸ ´ ao de Akaike. Os resultados mostram que ˜ o modelo autorregressivo de ordem 1 tem a melhor performance na previsao das receitas ˜ nas tres bases de dados. Comparando com o melhor modelo de machine learning em cada ˆ uma das bases de dados, este metodo consegue reduzir o erro em mais de 12 % e at ´ e 72 %. ´ Embora estes resultados precisem de investigac¸oes adicionais, de modo a abordar poss ˜ ´ıveis limitac¸oes, d ˜ ao-nos uma percec¸ ˜ ao geral sobre o desempenho de diversos modelos na pre- ˜ visao de receitas de empresas digitais, o que pode representar uma contribuic¸ ˜ ao valiosa para ˜ a tomada de decisoes dos neg ˜ ocios desta ind ´ ustria.Fernandes, Pedro AfonsoVeritati - Repositório Institucional da Universidade Católica PortuguesaPattenden, João Ribeiro dos Santos2023-09-11T08:13:00Z2023-07-052023-062023-07-05T00:00:00Zinfo:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/masterThesisapplication/pdfhttp://hdl.handle.net/10400.14/42245TID:203327683enginfo: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:RCAAP2023-09-19T01:41:54Zoai:repositorio.ucp.pt:10400.14/42245Portal AgregadorONGhttps://www.rcaap.pt/oai/openaireopendoar:71602024-03-19T20:28:58.743418Repositório 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 of corporate revenues with machine learning models versus traditional methods in the digital industry |
title |
Forecasting of corporate revenues with machine learning models versus traditional methods in the digital industry |
spellingShingle |
Forecasting of corporate revenues with machine learning models versus traditional methods in the digital industry Pattenden, João Ribeiro dos Santos Machine learning Sales and revenues forecasting Digital companies Pre-processing Time series Empirical comparison Accuracy Machine learning Previsão de vendas e receitas Pre-processamento Séries temporais Comparação Empresas digitais Domínio/Área Científica::Ciências Sociais::Economia e Gestão |
title_short |
Forecasting of corporate revenues with machine learning models versus traditional methods in the digital industry |
title_full |
Forecasting of corporate revenues with machine learning models versus traditional methods in the digital industry |
title_fullStr |
Forecasting of corporate revenues with machine learning models versus traditional methods in the digital industry |
title_full_unstemmed |
Forecasting of corporate revenues with machine learning models versus traditional methods in the digital industry |
title_sort |
Forecasting of corporate revenues with machine learning models versus traditional methods in the digital industry |
author |
Pattenden, João Ribeiro dos Santos |
author_facet |
Pattenden, João Ribeiro dos Santos |
author_role |
author |
dc.contributor.none.fl_str_mv |
Fernandes, Pedro Afonso Veritati - Repositório Institucional da Universidade Católica Portuguesa |
dc.contributor.author.fl_str_mv |
Pattenden, João Ribeiro dos Santos |
dc.subject.por.fl_str_mv |
Machine learning Sales and revenues forecasting Digital companies Pre-processing Time series Empirical comparison Accuracy Machine learning Previsão de vendas e receitas Pre-processamento Séries temporais Comparação Empresas digitais Domínio/Área Científica::Ciências Sociais::Economia e Gestão |
topic |
Machine learning Sales and revenues forecasting Digital companies Pre-processing Time series Empirical comparison Accuracy Machine learning Previsão de vendas e receitas Pre-processamento Séries temporais Comparação Empresas digitais Domínio/Área Científica::Ciências Sociais::Economia e Gestão |
description |
There has been a growing interest in the applicability of machine learning models in corporate sales and revenues forecasting. Past research has found promising results in this field, which show that these models might outperform more traditional methods. In this thesis, three real-world datasets containing information about the revenues and other fea tures of Amazon, Microsoft and Netflix in the last two decades are investigated to forecast the revenues of these digital companies. Firstly, we apply different pre-processing tech niques on the data, which include seasonal differencing using logarithm transformations. Then, some more classical time-series methods including Autoregressive model or order 1 are built. Moreover, different machine learning models including Partial Least Squares and Deep Neural network are applied. Finally, an empirical comparison of the models is performed using metrics such as Mean Absolute Error and Akaike Information Criterion. The results show that Autoregressive model of order 1 outperforms all the other models in terms of revenues forecasting accuracy in all datasets. Particularly, comparing with the benchmark machine learning model in each dataset, this method is able to reduce the error by more than 12 % and up to 72 %. Although these findings require further research to ad dress any possible limitations, they provide insights on the performance of several models in revenues forecasting of digital firms, which can be a valuable tool for the decision-making process of businesses in this industry. |
publishDate |
2023 |
dc.date.none.fl_str_mv |
2023-09-11T08:13:00Z 2023-07-05 2023-06 2023-07-05T00:00:00Z |
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/10400.14/42245 TID:203327683 |
url |
http://hdl.handle.net/10400.14/42245 |
identifier_str_mv |
TID:203327683 |
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_ |
1799133557634891776 |