Coleção de Artigos Acadêmicos
URI permanente para esta coleçãohttps://repositorio.insper.edu.br/handle/11224/3227
Navegar
6 resultados
Resultados da Pesquisa
Artigo Científico Validação de modelos de machine learning por experimentos estatísticos de campo(2024) Toaldo, Alexsandro; Vallim Filho, Arnaldo Rabello de Aguiar; Oyadomari, José Carlos Tiomatsu; Mendonça Neto, Octavio Ribeiro deObjetivo – Este artigo apresenta uma aplicação prática com o desenvolvimento de um experimento estatístico de campo em uma indústria de latas premium de alumínio nos Estados Unidos, visando validar estatisticamente resultados de modelos de machine learning (ML), previamente construídos. Metodologia: Usou-se conceitos de pesquisa intervencionista, que envolve experimentos de campo onde pesquisador e organização anfitriã atuam em conjunto buscando experimentar no sistema em estudo, e por meio da observação gerar conhecimento. Originalidade/Relevância: Sobre originalidade, não é frequente na literatura modelos de ML validados por experimento planejado de campo, seguido de análise estatística rigorosa. E a relevância da proposta se deve à sua contribuição para a literatura e pelas possibilidades de replicações do estudo em escala maior, na própria empresa ou em qualquer outra com desafios similares. Principais Resultados: Em fase anterior do estudo modelos de ML identificaram as variáveis de maior impacto em ineficiências (geração de sucata) em um processo de produção de latas de alumínio. Essas variáveis foram validadas nesta fase do estudo, através de experimento estatístico de campo, confirmando a significância estatística dos resultados do modelo de ML. Contribuições Teóricas e Práticas: A pesquisa contribui em termos práticos e científicos, pois a validação estatística de modelos de ML por experimentos planejados de campo é uma contribuição para a literatura de ciência aplicada, além de usas possibilidades práticas. Da mesma forma, apesar de amplamente utilizadas em diferentes áreas, pesquisas de cunho intervencionista ainda apresentam lacuna importante nas ciências sociais aplicadas, principalmente na gestão de processos industriais.Artigo Científico Neonatal mortality prediction with routinely collected data: a machine learning approach(2021) ANDRE FILIPE DE MORAES BATISTA; Diniz, Carmen S. G.; Bonilha, Eliana A.; Kawachi, Ichiro; Chiavegatto Filho, Alexandre D. P.Background: Recent decreases in neonatal mortality have been slower than expected for most countries. This study aims to predict the risk of neonatal mortality using only data routinely available from birth records in the largest city of the Americas. Methods: A probabilistic linkage of every birth record occurring in the municipality of São Paulo, Brazil, between 2012 e 2017 was performed with the death records from 2012 to 2018 (1,202,843 births and 447,687 deaths), and a total of 7282 neonatal deaths were identified (a neonatal mortality rate of 6.46 per 1000 live births). Births from 2012 and 2016 (N = 941,308; or 83.44% of the total) were used to train five different machine learning algorithms, while births occurring in 2017 (N = 186,854; or 16.56% of the total) were used to test their predictive performance on new unseen data. Results: The best performance was obtained by the extreme gradient boosting trees (XGBoost) algorithm, with a very high AUC of 0.97 and F1-score of 0.55. The 5% births with the highest predicted risk of neonatal death included more than 90% of the actual neonatal deaths. On the other hand, there were no deaths among the 5% births with the lowest predicted risk. There were no significant differences in predictive performance for vulnerable subgroups. The use of a smaller number of variables (WHO’s five minimum perinatal indicators) decreased overall performance but the results still remained high (AUC of 0.91). With the addition of only three more variables, we achieved the same predictive performance (AUC of 0.97) as using all the 23 variables originally available from the Brazilian birth records. Conclusion: Machine learning algorithms were able to identify with very high predictive performance the neonatal mortality risk of newborns using only routinely collected data.Artigo Científico Cause-specific mortality prediction in older residents of São Paulo, Brazil: a machine learning approach(2021) Nascimento, Carla Ferreira do; Hellen Geremias dos Santos; ANDRE FILIPE DE MORAES BATISTA; Lay, Alejandra Andrea Roman; Duarte, Yeda Aparecida OliveiraBackground: Populational ageing has been increasing in a remarkable rate in developing countries. In this scenario, preventive strategies could help to decrease the burden of higher demands for healthcare services. Machine learning algorithms have been increasingly applied for identifying priority candidates for preventive actions, presenting a better predictive performance than traditional parsimonious models. Methods: Data were collected from the Health, Well Being and Aging (SABE) Study, a representative sample of older residents of São Paulo, Brazil. Machine learning algorithms were applied to predict death by diseases of respiratory system (DRS), diseases of circulatory system (DCS), neoplasms and other specific causes within 5 years, using socioeconomic, demographic and health features. The algorithms were trained in a random sample of 70% of subjects, and then tested in the other 30% unseen data. Results: The outcome with highest predictive performance was death by DRS (AUC−ROC = 0.89), followed by the other specific causes (AUC−ROC = 0.87), DCS (AUC−ROC = 0.67) and neoplasms (AUC−ROC = 0.52). Among only the 25% of individuals with the highest predicted risk of mortality from DRS were included 100% of the actual cases. The machine learning algorithms with the highest predictive performance were light gradient boosted machine and extreme gradient boosting. Conclusion: The algorithms had a high predictive performance for DRS, but lower for DCS and neoplasms. Mortality prediction with machine learning can improve clinical decisions especially regarding targeted preventive measures for older individuals.Artigo Científico Data Leakage in Health Outcomes Prediction With Machine Learning. Comment on “Prediction of Incident Hypertension Within the Next Year: Prospective Study Using Statewide Electronic Health Records and Machine Learning"(2021) Chiavegatto Filho, Alexandre; ANDRE FILIPE DE MORAES BATISTA; Santos, Hellen Geremias dosArtigo Científico Deep learning models for inflation forecasting(2023) Theoharidis, Alexandre Fernandes; DIOGO ABRY GUILLEN; HEDIBERT FREITAS LOPES; Hosszejni, DarjusWe propose a hybrid deep learning model that merges Variational Autoencoders and Convolutional LSTM Networks (VAE-ConvLSTM) to forecast inflation. Using a public macroeconomic database that comprises 134 monthly US time series from January 1978 to December 2019, the proposed model is compared against several popular econometric and machine learning benchmarks, including Ridge regression, LASSO regression, Random Forests, Bayesian methods, VECM, and multilayer perceptron. We find that VAE-ConvLSTM outperforms the competing models in terms of consistency and out-of-sample performance. The robustness of such conclusion is ensured via cross-validation and Monte-Carlo simulations using different training, validation, and test samples. Our results suggest that macroeconomic forecasting could take advantage of deep learning models when tackling nonlinearities and nonstationarity, potentially delivering superior performance in comparison to traditional econometric approaches based on linear, stationary models.- Extracting value from Brazilian Court decisions(2022) Fernandes, William Paulo Ducca; Frajhof, Isabella Zalcberg; GUILHERME DA FRANCA COUTO FERNANDES DE ALMEIDA; Rodrigues, Ariane Moraes Bueno; Barbosa, Simone Diniz Junqueira; Konder, Carlos Nelson; Nasser, Rafael Barbosa; Carvalho, Gustavo Robichez de; Lopes, Hélio Côrtes VieiraWe propose a methodology to extract value from Brazilian Court decisions to support judges and lawyers in their decision-making. We instantiate our methodology in one information system we have developed. Such system (i) extracts plaintiff’s legal claims and each specific provision on legal opinions enacted by lower and Appellate Courts, and (ii) connects each legal claim with the corresponding judicial provision. The information system presents the results through visualizations. Information Extraction for legal texts has been previously approached in the literature for different languages, using different methods. Our proposal is different from previous work, since our corpora comprise Brazilian lower and Appellate Court decisions, in which we look for a set of plaintiff’s legal claims and judicial provisions commonly judged by the Court. We use the following methods to tackle the information extraction tasks: Bidirectional Long Short-Term Memory network; Conditional Random Fields; and a combination of Bidirectional Long Short-Term Memory network and Conditional Random Fields. In addition to the well-known distributed representation of words in word embeddings, we use character-level representation of words in character embeddings. We have built three corpora – Kauane Insurance Report, Kauane Insurance Lower, and Kauane Insurance Upper – to train and evaluate the system, using public data from the State Court of Rio de Janeiro. Our methods achieved good quality for Kauane Insurance Lower and Kauane Insurance Upper, and promising results for Kauane Insurance Report.