TCC - Bacharelado em Sistemas da Informação (Sede)
URI permanente para esta coleçãohttps://arandu.ufrpe.br/handle/123456789/427
Navegar
84 resultados
Resultados da Pesquisa
Item Aprendizagem de máquina para a identificação de clientes propensos à compra em Inbound marketing(2019-07-12) Silva, Bruno Roberto Florentino da; Monteiro, Cleviton Vinicius Fonsêca; Soares, Rodrigo Gabriel Ferreira; http://lattes.cnpq.br/2526739219416964; http://lattes.cnpq.br/9362573782715504The most important point for a company should always be the customer and getting new customers is not always an easy strategy. Digital marketing techniques study how to attract new customers to businesses using digital platforms. By virtue of the popularization of these means, the strategies had to be shaped to the new possibilities. With just one click you can reach thousands of individuals, which means many new leads for the company. However, filtering out which of these individuals are really interested in the product or service offered by the company demands a lot of effort from the sales team. This overhead is detrimental in the sense that the company can lose revenue by not targeting the real opportunities. With the aim to minimize this problem, the present work offers a proposal whose objective is the automatic identification of the client achieved through digital marketing strategies. It is proposed the usage of Machine Learning techniques, in particular supervised classification algorithms, namely Decision Tree and Naive Bayes. It was used the Scikit-learn library available for the Python programming language. In addition, it was necessary to apply the SMOTE oversampling algorithm, due to the unbalance of the dataset. In addition, in order to optimize the classification, we used the techniques of attribute selection and model selection with hyperparameters adjustment. Finally, to evaluate the results, we used the confusion matrix, the precision and coverage metrics, and the accuracy and coverage curve. Due to the imbalance of the data, the precision metric did not report good indexes results, with averages of 5.5% of correctness. In addition, the coverage was around 83%. Even with such divergent results among the applied metrics, the present work reached its goal, identifying most of the real opportunities and reporting that using this approach, it would be possible to obtain a reduction of up to 85% in the effort applied by the sales team if they had to call for all the leads. As a consequence, the company may have a cost reduction with the resources applied to obtain new customers, allowing the sales team to find new customers with greater efficiency.Item Como o uso de Play Feature Delivery no Android pode ajudar na sustentabilidade digital(2023-09) Claudino, Yasmmin Maria Monteiro; Albuquerque Júnior, Gabriel Alves de; http://lattes.cnpq.br/1399502815770584; http://lattes.cnpq.br/0549149216731460With the increasing access to the internet via mobile devices among the less privileged classes in Brazil, digital sustainability becomes of growing importance. The aim of this study is to assess the impact of the Play Feature Delivery technology on mobile data consumption on Android devices. A parametric t-test was applied to evaluate significant differences between the averages of data amounts spent in Megabytes when downloading two applications. The result corresponded to a t-value of approximately 65.55 and the rejection of the null hypothesis. This finding not only underscores the technical importance for Android developers but also highlights its relevance in showing an improvement in mobile data usage, especially in an era where the democratization of access to information is vital. The research reinforces the idea that society should adapt to digital resources, optimizing data usage. To reach these conclusions, two mobile applications focused on first aid guidelines were developed and analyzed. The main advantage observed was the reduction in mobile data consumption, validating the efficacy of Play Feature Delivery compared to conventional applications.Item Construção de pipelines de dados sobre obras públicas em Pernambuco: abordagem prática com o Apache Airflow(2023-09-21) Silva, Henrique César José da; Albuquerque Júnior, Gabriel Alves de; http://lattes.cnpq.br/1399502815770584This study presents a practical approach to building data pipelines focused on collecting, transforming, and storing information related to public works in the state of Pernambuco. The central objective is to develop efficient and automated workflows for extracting data from public transparency portals and subsequently consolidating this information. Based on Data Engineering technologies, the Apache Airflow framework was chosen to orchestrate the processes, enabling the scheduling and monitoring of these workflows.Item Uso de Machine Learn para classificação de lançamentos financeiro: estudo comparativo entre modelo AutoML e Redes MLP(2022-10-10) Silva, Vinicius Mateus Mendonça da; Monteiro, Cleviton Vinicius Fonsêca; http://lattes.cnpq.br/9362573782715504; http://lattes.cnpq.br/6180002649065928The study of this work aims to help companies in their financial management by generating models based on Machine Learning to classify financial releases. With the help of libraries developed in the Python language, it was possible to train AutoML models and Multilayer Perceptron Neural Networks responsible for data classification. With results above 85% in the metrics of Accuracy, Recall, F-measure and Precision for both models, using them brings the possibility of better management of financial releases with less effort.Item Técnicas de comitês para a estimação de esforço na correção de software(2019-12-10) Guimarães, Ariana Lima; Soares, Rodrigo Gabriel Ferreira; http://lattes.cnpq.br/2526739219416964; http://lattes.cnpq.br/2605671850587343A well-defined planning of a software project, since the early stages, is indispensable to its success, whether the development refers to product’s creation or maintenance. Accordingly to the software life cycle, maintenance is continuously executed after the product’s building and delivery, in parallel to the tests execution by engineers and/or users. In this stage, User Stories and Issue Reports are the first documents to be presented. These documents describe, in natural language, business requirements, error scenarios found, expected corrections and enhancements for the system. Its objectives are, among other things, ranking the activities needed to be accomplish during the project. Therefore, in line with the available resources – human, financial and temporal -, it is possible to estimate the effort that will be necessary in the activities development and generate essential information for an effective and efficient planning. As these documents are written in natural texts, it raises the opportunity to use Natural Language Processing and Machine Learning (ML) to predict software effort. In practice, in the daily life of software factories, it is common to use experts’ and project staff’s opinion to judge the effort required by an activity during Planning Poker sessions. Usually, in this technique, the effort is measured in Story Points, which follow Fibonacci sequence. But this planning model requires the scaling of more resources to be executed. The application of ML causes in a system, after the learning phase, the ability to seize the team experience and replicate it quickly and automatically to estimate the activities effort. Thus, this work covers the ML field, proposing a PV-DM Ensemble approach to extract features of Issue Reports to estimate Story Points, the effort indicator. Compared to the two other approaches of BoW and simple PV-DM, the proposed technique has presented good results, about 80% of f-measure, in a supervised learning SVM classifier. The experiments results proved to be a starting point for further study of PV-DM Ensemble approach and its improvement.Item An implementation of a mathematical-computational method for the detection and treatment of financial outliers in higher education(2023-09-06) Freitas, Nathan Cavalcante; Gouveia, Roberta Macêdo Marques; http://lattes.cnpq.br/2024317361355224; http://lattes.cnpq.br/1613649528791400The Higher Education Census occurs annually, collecting data from public and private Higher Educational Institutions (HEI) in Brazil. Different factors can lead to anomalies or outliers in some of these collected data. This work proposes a mathematical-computational method to detect and treat atypical HEI’s financial values. Both univariate and bivariate analysis to that end. We analyzed the expenses and incomes of HEI in the census from 2016 to 2019. This analysis revealed that 204 out of 2,224 HEI, approximately 10%, reported some atypical data.Item Geração de indicadores de desempenho de negócio utilizando o Data Warehouse de uma grande rede de varejo(2023-05-04) Tavares, Luís Felipe do Carmo Costa; Gouveia, Roberta Macêdo Marques; http://lattes.cnpq.br/2024317361355224The use of Key Performance Indicators (KPIs) is essential for companies as it allows them to evaluate the performance and outcome of processes, facilitate decision-making, identify patterns of sector performance, reduce unnecessary costs, and increase operational efficiency. However, it is important to take into account that the calculation of KPIs becomes more complex due to the company's growth and the arrival of new demands. This project was implemented in a large retail network that needed to reformulate the way it calculated its KPIs due to the emergence of new branches and an increase in employees. To improve performance, the centralization of calculations was performed through a Data Warehouse model (with Data Lakes), where calculations with changes are being performed in a single database instead of in each branch's individual database and later centralized. During the project's implementation, several challenges were faced, such as validating the result of each indicator, creating new features (such as cumulative calculation), and the need to create a specific procedure for each metric and indicator.Item Desenvolvimento de uma plataforma de compartilhamento e análise de Dados com ênfase em LGPD(2023-04-27) Monteiro, Heitor Augusto Gomes; Medeiros, Victor Wanderley Costa de; http://lattes.cnpq.br/7159595141911505Item Desenvolvimento de um plug-in para a replicação de dados entre os sistemas NetBox e ServiceNow CMDB(2023-05-03) Silva Júnior, Manassés Júlio da; Gouveia, Roberta Macêdo Marques; http://lattes.cnpq.br/2024317361355224This work presents a new plugin developed to integrate the open source network configuration software NetBox with the ServiceNow CMDB. This plugin extends the functionality of NetBox, allowing users to send NetBox data to the ServiceNow API. NetBox is an open source web application that helps manage and document computer networks. It acts as a centralized repository for network infrastructure information, including device inventory, IP address management, cable management, and power management. On the other hand, the ServiceNow CMDB is a central repository that contains information about all assets and configuration items in an organization's IT infrastructure. The integration between these platforms is achieved through the creation of plugins that extend the functionality of NetBox, allowing it to work together with the ServiceNow CMDB. The project uses Python as the main language, the Django web framework, and Docker to create the development environment. Overall, this project provides a powerful and flexible tool for network administrators and operators to manage their network infrastructure. The plugin architecture follows the Django MTV (Model-View-Template) architecture, where the Model represents the data and database schema, the View handles requests and responses, and the Template generates the HTML output. The main functionality of the project is the automatic replication of Create, Read, Update and Delete (CRUD) modifications in selected objects from NetBox to the ServiceNow CMDB, done through the ServiceNow API. This automatic replication feature uses Webhooks to monitor object modifications, and the plugin automatically handles the creation and deletion of Webhooks. Other features include manual batch and simulation for replicating data to the CMDB. The visual interface of the plugin is simple and focused on its functionalities.Item Transformação digital: eliminação do uso de papel em organizações através da integração de sistemas de BPM, gestão de processos eletrônicos e gerenciamento de recursos humanos(2022-10-13) Barros, Gutenberg Duarte Neves de; Vilar, Guilherme; http://lattes.cnpq.br/4618755191948983; http://lattes.cnpq.br/6466753248629314