Geovanne Oliveira Alves
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Research Interests
Geovanne Oliveira Alves has a total of 22 co-authors. Here are the top co-authors by number of shared publications:
- Alexandre Magno Andrade Maciel
Universidade de Pernambuco
2 shared publications - Lubnnia Souza
Universidade de Pernambuco, Recife, Brazil
2 shared publications - Erika Carlos Medeiros
Doutora em Ciência da Computação Universidade Federal de Pernambuco (UFPE) Recife Pernambuco Brasil
1 shared publication Fernando Ferreira de Carvalho
University of Pernambuco, Caruaru, PE, Brazil and Federal Institute of Science and Technology of Pernambuco, Recife, PE, Brazil
1 shared publicationFernando Pontual de Souza Leão Junior
University of Pernambuco, Caruaru, PE, Brazil
1 shared publication- Gabriela De Vasconcelos
University of Pernambuco
1 shared publication
Latest Publications
- Open Access
- 10 June 2024
- Published by Scholar Publishing in Archives of Business Research
- Vol. 12 (6) , 12-44
Unlocking Retail Success: Empowering Decision-Making with Advanced Sales Forecast Models
The gross revenue indicator contributes to the understanding of the company’s situation, and generating sales revenue forecasts is a strategy that helps the manager in directing the business. This work aims to develop a set of Machine Learning (ML) models to forecast sales in physical retail. Methodology – To carry out this work, a methodology was proposed to create, compare and evaluate ML models. Findings – When analyzing the forecast scenarios, it was observed that Hourly forecasts performed better than Day forecasts. We highlight the LIGHTGBM model, which presented the best scores in the F1-score metric with 82.95%, 79.26% and 76.53% scenario representing one hour, two hours and three hours ahead, respectively. Value – It is expected that the forecast models will help managers to find insights to support the operational decisions of physical retail contributing to carry out actions to optimize companies’ processes.
- 10 June 2024
- Published by Scholar Publishing in Archives of Business Research
- Vol. 12 (6) , 12-44
Open AccessUnlocking Retail Success: Empowering Decision-Making with Advanced Sales Forecast Models
The gross revenue indicator contributes to the understanding of the company’s situation, and generating sales revenue forecasts is a strategy that helps the manager in directing the business. This work aims to develop a set of Machine Learning (ML) models to forecast sales in physical retail. Methodology – To carry out this work, a methodology was proposed to create, compare and evaluate ML models. Findings – When analyzing the forecast scenarios, it was observed that Hourly forecasts performed better than Day forecasts. We highlight the LIGHTGBM model, which presented the best scores in the F1-score metric with 82.95%, 79.26% and 76.53% scenario representing one hour, two hours and three hours ahead, respectively. Value – It is expected that the forecast models will help managers to find insights to support the operational decisions of physical retail contributing to carry out actions to optimize companies’ processes.
- 22 November 2021
- Published by Sociedade Brasileira de Computação
- p. 35-47
Are we ready? Identifying the gap between academia and software industry in the context of agile methodologies
Nowadays, there is an exponential increase in the technology industry. However, there is not enough movement to promote changes in the Computer Science curricula. This study aims to analyze the alignment between Brazilian northeast academia and the global industry regarding developing skills in the context of agile methods. This research conducted an exploratory and quantitative survey with 161 participants represented by 65 students, 85 professionals from 10 countries, and 16 university professors. The preliminary results illustrate that academics believe that they are moderately aligned with the market. However, from the practitioner's viewpoint, it is unsatisfactory. This article reports relevant findings that can help the Brazilian academy align its practices with the needs of the global software industry.
- 22 November 2021
- Published by Sociedade Brasileira de Computação
- p. 35-47
Are we ready? Identifying the gap between academia and software industry in the context of agile methodologies
Nowadays, there is an exponential increase in the technology industry. However, there is not enough movement to promote changes in the Computer Science curricula. This study aims to analyze the alignment between Brazilian northeast academia and the global industry regarding developing skills in the context of agile methods. This research conducted an exploratory and quantitative survey with 161 participants represented by 65 students, 85 professionals from 10 countries, and 16 university professors. The preliminary results illustrate that academics believe that they are moderately aligned with the market. However, from the practitioner's viewpoint, it is unsatisfactory. This article reports relevant findings that can help the Brazilian academy align its practices with the needs of the global software industry.
- 4 October 2021
- Published by Sociedade Brasileira de Computação
- p. 41-48
Evaluation of Machine Learning Models for Estimating Sales in Physical Retail
The amount of sales in a store is a strong indicator that contributes to managers' decision making. In physical retail, unlike e-commerce, it is more difficult to collect sales and customer behavior metrics because it depends on great sensing and integration between systems. In a shopping mall scenario, we use real WiFi data, People Flow and Sales create a dataset. In this article we propose an evaluation of machine learning models with the objective of estimating the next hour sales in Low, Medium and High, thus providing a tool to assist in decision making. We use the PyCaret library to perform the training of the 13 compared algorithms. The F1-score metric was used to evaluate the models. The Gradient Booster Classifier was the model that got the best result with a score of 84.75%. Among the estimated classes, the High class showed the greatest error in the confusion matrix, reaching 60%, possibly a reflection of the low amount of records in the high class.
- 4 October 2021
- Published by Sociedade Brasileira de Computação
- p. 41-48
Evaluation of Machine Learning Models for Estimating Sales in Physical Retail
The amount of sales in a store is a strong indicator that contributes to managers' decision making. In physical retail, unlike e-commerce, it is more difficult to collect sales and customer behavior metrics because it depends on great sensing and integration between systems. In a shopping mall scenario, we use real WiFi data, People Flow and Sales create a dataset. In this article we propose an evaluation of machine learning models with the objective of estimating the next hour sales in Low, Medium and High, thus providing a tool to assist in decision making. We use the PyCaret library to perform the training of the 13 compared algorithms. The F1-score metric was used to evaluate the models. The Gradient Booster Classifier was the model that got the best result with a score of 84.75%. Among the estimated classes, the High class showed the greatest error in the confusion matrix, reaching 60%, possibly a reflection of the low amount of records in the high class.
- Open Access
- 15 April 2021
- Published by MDPI AG in Informatics
- Vol. 8 (2) , 27
Benchmarking Machine Learning Models to Assist in the Prognosis of Tuberculosis
Tuberculosis (TB) is an airborne infectious disease caused by organisms in the Mycobacterium tuberculosis (Mtb) complex. In many low and middle-income countries, TB remains a major cause of morbidity and mortality. Once a patient has been diagnosed with TB, it is critical that healthcare workers make the most appropriate treatment decision given the individual conditions of the patient and the likely course of the disease based on medical experience. Depending on the prognosis, delayed or inappropriate treatment can result in unsatisfactory results including the exacerbation of clinical symptoms, poor quality of life, and increased risk of death. This work benchmarks machine learning models to aid TB prognosis using a Brazilian health database of confirmed cases and deaths related to TB in the State of Amazonas. The goal is to predict the probability of death by TB thus aiding the prognosis of TB and associated treatment decision making process. In its original form, the data set comprised 36,228 records and 130 fields but suffered from missing, incomplete, or incorrect data. Following data cleaning and preprocessing, a revised data set was generated comprising 24,015 records and 38 fields, including 22,876 reported cured TB patients and 1139 deaths by TB. To explore how the data imbalance impacts model performance, two controlled experiments were designed using (1) imbalanced and (2) balanced data sets. The best result is achieved by the Gradient Boosting (GB) model using the balanced data set to predict TB-mortality, and the ensemble model composed by the Random Forest (RF), GB and Multi-Layer Perceptron (MLP) models is the best model to predict the cure class.
- 15 April 2021
- Published by MDPI AG in Informatics
- Vol. 8 (2) , 27
Open AccessBenchmarking Machine Learning Models to Assist in the Prognosis of Tuberculosis
Tuberculosis (TB) is an airborne infectious disease caused by organisms in the Mycobacterium tuberculosis (Mtb) complex. In many low and middle-income countries, TB remains a major cause of morbidity and mortality. Once a patient has been diagnosed with TB, it is critical that healthcare workers make the most appropriate treatment decision given the individual conditions of the patient and the likely course of the disease based on medical experience. Depending on the prognosis, delayed or inappropriate treatment can result in unsatisfactory results including the exacerbation of clinical symptoms, poor quality of life, and increased risk of death. This work benchmarks machine learning models to aid TB prognosis using a Brazilian health database of confirmed cases and deaths related to TB in the State of Amazonas. The goal is to predict the probability of death by TB thus aiding the prognosis of TB and associated treatment decision making process. In its original form, the data set comprised 36,228 records and 130 fields but suffered from missing, incomplete, or incorrect data. Following data cleaning and preprocessing, a revised data set was generated comprising 24,015 records and 38 fields, including 22,876 reported cured TB patients and 1139 deaths by TB. To explore how the data imbalance impacts model performance, two controlled experiments were designed using (1) imbalanced and (2) balanced data sets. The best result is achieved by the Gradient Boosting (GB) model using the balanced data set to predict TB-mortality, and the ensemble model composed by the Random Forest (RF), GB and Multi-Layer Perceptron (MLP) models is the best model to predict the cure class.
- Open Access
- 1 April 2021
- Published by Revista de Engenharia e Pesquisa Aplicada in Revista de Engenharia e Pesquisa Aplicada
- Vol. 6 (3) , 12-20
Estudo Comparativo de Técnicas de Previsão para Casos de Dengue
A dengue é uma infecção viral que se espalha rapidamente e é endêmica em mais de 100 países tropicais e subtropicais da África, América e regiões da Ásia-Pacífico. Geralmente, a epidemiologia da dengue é influenciada por uma complexa interação de fatores que incluem rápida urbanização e aumento da densidade populacional, capacidade dos sistemas de saúde, eficácia dos sistemas de controle de vetores, limpeza urbana etc. No Brasil que é considerado um país tropical, há uma incidência de casos crescente nos últimos anos, em específico na capital Pernambucana Recife há um ambiente propício para o aumento expressivo dos casos de dengue como são apresentados pelo Boletim Epidemiológico da Secretaria de Vigilância em Saúde do Ministério da Saúde. O presente trabalho apresenta um estudo comparativo de técnicas de Mineração de Dados seguindo a abordagem CRISP-DM, para um modelo de previsão de casos de Dengue no Recife-PE.
- 1 April 2021
- Published by Revista de Engenharia e Pesquisa Aplicada in Revista de Engenharia e Pesquisa Aplicada
- Vol. 6 (3) , 12-20
Open AccessEstudo Comparativo de Técnicas de Previsão para Casos de Dengue
A dengue é uma infecção viral que se espalha rapidamente e é endêmica em mais de 100 países tropicais e subtropicais da África, América e regiões da Ásia-Pacífico. Geralmente, a epidemiologia da dengue é influenciada por uma complexa interação de fatores que incluem rápida urbanização e aumento da densidade populacional, capacidade dos sistemas de saúde, eficácia dos sistemas de controle de vetores, limpeza urbana etc. No Brasil que é considerado um país tropical, há uma incidência de casos crescente nos últimos anos, em específico na capital Pernambucana Recife há um ambiente propício para o aumento expressivo dos casos de dengue como são apresentados pelo Boletim Epidemiológico da Secretaria de Vigilância em Saúde do Ministério da Saúde. O presente trabalho apresenta um estudo comparativo de técnicas de Mineração de Dados seguindo a abordagem CRISP-DM, para um modelo de previsão de casos de Dengue no Recife-PE.