Industrial and Manufacturing Engineering, Management Science and Operations Research
4
Scopus Publications
Scopus Publications
Assessment of Higher Education Institutions in the Rio de Janeiro based on RUF Rankings: An Application of the Thor 2 Method Wagner Dos Anjos Carvalho, Nayara Tavares Cardoso, Marcos Paulo Rosa Lima Da Silva, Marcos Dos Santos, Carlos Francisco Simões Gomes Proceedings 2024 5th International Conference on Mobile Computing and Sustainable Informatics Icmcsi 2024, 2024 The ranking method of higher education institutions use indicators to provide an overall performance analysis based on the scientific contribution of faculty, the relevance of research in the institution, and the quality of graduates' integration into the job market. This research study proposes the use of the Multicriteria Decision Support Method THOR 2 for selecting the best universities in the Rio de Janeiro, in accordance with the indicators used by the Folha University Ranking (RUF). The data, collected directly from the websites of each institution, include 203 universities, comprising federal, state, municipal, and private institutions, with 5 criteria. However, the research will be limited to institutions located in the Rio de Janeiro, totaling 17 institutions. The THOR 2 method, through the computational tool THOR Web, determined that the Federal University of Rio de Janeiro (UFRJ), Federal Fluminense University (UFF), the State University of Rio de Janeiro (UERJ), and the Pontifical Catholic University of Rio de Janeiro (PUC-Rio) are the highest ranked in the Rio de Janeiro.
Optimization Algorithm for Creating Price Tiers in The Customer Migration Process Between Companies Carlos Eduardo Alves Ribeiro, Wagner Dos Anjos Carvalho, Luana de Azevedo de Oliveira, Emerson Hissao Kojima, Luiz Paulo Fávero, Marcos Dos Santos Proceedings of the 3rd International Conference on Applied Artificial Intelligence and Computing Icaaic 2024, 2024 This research study reviews the application of optimization algorithms for a case of customer migration between two telecommunications companies. In this scenario, a group of customers was migrated from one company to another, with some changes in their subscription fees. The goal was to determine the values that would minimize the revenue loss for the company receiving these customers. This analysis applied heuristic optimization methods in a hybrid form, utilizing a Genetic Algorithm [GA] combined with a Particle Swarm Optimization Algorithm [PSO] to find an optimal solution. This hybrid method, called Swarm Genetic Algorithm [SGA] aimed to leverage the high exploration capacity of the GA and the high exploitation capacity of the PSO to identify local minima. The study also established a predictive model to assess whether the final pricing would impact customer satisfaction, assisting the business area in deciding how many price points should be created. After the execution of the final algorithm, an optimal solution was found, resulting in a 48% reduction in revenue loss after the migration process and a 1.7% increase in monthly gross revenue post-optimization.
Application of a machine learning model to maximize the success rate in day trade operations on the American Stock Exchange Wagner A. Carvalho, Marcelo Henrique C. Cerqueira, Luana de Azevedo de Oliveira, Carlos Francisco Santos Simões, Luiz Paulo Fávero, Marcos dos Santos Procedia Computer Science, 2024 Daytrading has been showing a growing popularity in the world due to easy access via technology, the possibility of additional earnings and a large increase in courses and several mentors available on social networks. This scenario causes many people to be unprepared to enter this market that has a high risk and that end up causing many people to lose their savings. Considering this situation, this study proposes the analysis of the data of a daytrade strategy, applying a machine learning model to help the investor make better decisions. Data from November 2020 to July 2023 was used within the US market based on the company [AMD]. The method used was the supervised machine learning technique known as the decision tree model, which seeks to identify the probability of event and non-event within the scenarios proposed in this work. The results were analyzed using the confusion matrix, gauging the accuracy in the training and test base, applying several decision tree models in order to find the best model and accuracy in the test base. In this sense, an improvement in the assertiveness rate was observed with the application of the supervised machine learning model based on a decision tree.
Evaluation of the relative efficiency of broiler housing facilities using Data Envelopment Analysis Wagner dos Anjos Carvalho, Isabella de Castro Minhaneli, Renato Milhomem de Oliveira Filho, Luana de Azevedo de Oliveira, Emerson Hissão Kojima, Ana Amelia Mendonça, Célio Manso de Azevedo Junior, Marcos dos Santos Procedia Computer Science, 2024 This research aimed to observe the efficiency of productive units of broiler chickens using Data Envelopment Analysis (DEA) with the CCR model. This technique aims to define an efficiency frontier from the process’s inputs and outputs, which can be used to evaluate the relative efficiency of the studied units and to define consistent goals to the units bellow the expected performance, comparing units of the same technology profile and scale. The study identified benchmark units as performance reference in order the improve the organization’s results level, increasing productivity and reducing costs. Twenty-five production units were examined in aviaries with automated technology, located in the Center-West region of Brazil, of which 23 presented global inefficiency, with potential to increase the volume of meat produced with the same amount of inputs. The units that contained only male birds presented the highest global efficiencies, followed by the mixed units and, at last, the units that contained only female birds. The units with the lowest efficiency rates were the ones with the highest mortality rates (3.3 and 4.05%). Several other factors can contribute to these results, such as, possible human errors ant the equipment’s adjustments and the employment of correct husbandry techniques. Investigating the low performance causes is necessary for the company to design a strategy of performance improvement.
