Maestría en Ciencias de los Datos y Analítica (tesis)
URI permanente para esta colección
Examinar
Envíos recientes
Ítem Cotton Price Long-Term Time Series Forecasting : A look at Transformers Suitability(Universidad EAFIT, 2024) Salazar Escobar, Carlos Enrique; Olarte, TomásRecent years have witnessed a surge of Transformer-based models for long-term time series forecasting (LTSF). These models boast impressive results in Natural Language Processing (NLP) and Computer Vision (CV), but their effectiveness in capturing the crucial temporal order inherent in time series data remains a question. This work investigates the suitability of Transformer-based models for long-term commodity price prediction, by replicating the work presented in "Are Transformers Effective for Time Series Forecasting?" by Zeng et al. (2022). We aim to evaluate their effectiveness compared to simpler baselines and analyze their limitations in capturing long-range dependencies. By delving deeper into these limitations, this research seeks to contribute to the development of more effective forecasting models for commodity price prediction.Ítem Predicción de la demanda de repuestos para vehículos pesados : un enfoque de estimación no paramétrico(Universidad EAFIT, 2024) Cardona Delgado, David Andrés; Laniado Rodas, Henry; Zuluaga Díaz, Francisco IvánÍtem Desarrollo de un Score de riesgo financiero con XGBoost para evaluación de crédito Fintech(Universidad EAFIT, 2024) Correa Restrepo, Juan David; Ortiz Arias, SantiagoÍtem Análisis de riesgo de impago en el sector financiero : enfoque en tarjetas de crédito(Universidad EAFIT, 2024) Herrera Olivares, Maher Stehisy; Moreno Reyes, Nicolás AlbertoÍtem Identificación de anomalías en el aislamiento de líneas de transmisión a partir de imágenes(Universidad EAFIT, 2024) Sánchez Echeverri, Daniel Alonso; Martínez Vargas, Juan David; Valencia Díaz, EdisonCurrently, the maintenance of electric power transmission lines is based on inspection tasks that require long journeys over complex terrain to determine the condition of this infrastructure. Technological advances in unmanned aerial vehicles, also known as drones, have allowed some inspection tasks to be performed remotely, capturing photographs of the infrastructure. These images are then analyzed to identify the physical condition of the assets. However, processing and visualization is a manual procedure that requires hours of review to identify problems. In this context, the present work proposes the use of artificial vision algorithms, in order to identify the elements of the network that present anomalies, affecting the normal operation of the electric power transmission system. With this strategy, it is expected to improve the efficiency in the identification of problems in the electric power infrastructure, reducing the time and costs associated with the manual review of the images obtained by the drones. The dataset has been obtained from a company in the electric power sector in Colombia. In this paper, for reasons of data protection and business ethics, the company has been anonymized and renamed as Empresa de Energía EE.Ítem Modelos de clasificación de emociones basados en CNN y ViT(Universidad EAFIT, 2024) Ruiz Ramírez, Santiago; Montoya Múnera, Edwin NelsonThe present project focuses on comparing the performance of convolutional neural network (CNN) and vision transformer (ViT) models to classify emotions in facial images. The problem lies in the accuracy of CNNs, which still faces challenges, while ViTs have emerged as a promising alternative, highlighting the importance of addressing emotions in the context of mental health, as these can influence the ability to creative work and are linked to different clinical study conditions.Ítem Análisis y predicción de ventas de motos haciendo uso de la metodología “Customer Value Map” y técnicas de Machine Learning(Universidad EAFIT, 2024) Díaz Cordero, Sandra Marcela; Martínez Vargas, Juan David; Vallejo Correa, Paola AndreaÍtem Análisis de registros de mantenimiento de centrales de generación de energía con técnicas de procesamiento de lenguaje natural(Universidad EAFIT, 2024) Ocampo Davila, Andrés Alonso; Salazar Martínez, Carlos AndresÍtem Un marco de trabajo para gobierno de datos. Caso de estudio : Empresa de Transmisión y Distribución de Energía(Universidad EAFIT, 2024) Hernández Montoya, María Margarita; Tabares Betancur, Marta Silvia del SocorroÍtem Optimización de cartera de activos financieros utilizando Markowitz y Black-Litterman : una perspectiva desde la computación cuántica(Universidad EAFIT, 2024) Jaramillo Pineda, Carlos Andrés; Almonacid Hurtado, Paula María; Lalinde Pulido, Juan GuillermoQuantum computing, currently in its emerging stage, holds the potential to revolutionize various sectors, including finance. While portfolio optimization strategies based on classical methods like Markowitz and Black Litterman have already proven effective, the introduction of quantum algorithms could significantly enhance these techniques in terms of predictive ability and computational efficiency. Building upon previous research such as that by Bova (2021), which underlines the crucial role that quantum computing could play given the volume and complexity of financial data, this paper proposes a framework that integrates classical Markowitz and Black-Litterman theories with quantum computing. Through this hybrid approach, we explore how hybrid classic-quantum algorithms approaches can enrich the portfolio optimization process, offering significant advantages in financial analysis and strategic decision-making.Ítem Imágenes satelitales de luces nocturnas como proxy del valor agregado de los municipios del departamento de Antioquia(Universidad EAFIT, 2024) Marín Castaño, Kevin Stiv; Almonacid Hurtado, Paula MaríaÍtem Dependencia espacial en el riesgo de crédito. Análisis espacial para el caso de Medellín(Universidad EAFIT, 2024) Castro Castaño, Esteban; García Cruz, Gustavo AdolfoÍtem A Multivariate Outlier Detection Methodology Based on S-Orthogonal DOBIN Projections(Universidad EAFIT, 2024) Cano Campiño, Andrés Mauricio; Ortiz Arias, SantiagoÍtem Open cluster membership using robust and non-parametric statistical methods(Universidad EAFIT, 2024) Madrid Álvarez, Simón; Laniado, Henry; Muñoz, Juan CarlosÍtem Flujo de trabajo basado en Procesamiento de Lenguaje Natural (PLN) para la extracción de insights del contenido generado por usuarios (CGU). Caso de estudio aplicado a una fintech(Universidad EAFIT, 2024) Barrera Ravelo, Angie Karina; Montoya Múnera, Edwin NelsonÍtem Analizando patrones de éxito en YouTube : un sistema de recomendación para creadores de contenidos educativos(Universidad EAFIT, 2024) Osorio Urrea, Vanessa; Ortiz Arias, Santiago; del Castillo Cortázar, Francisco JavierÍtem Predicción del rendimiento de cultivos agrícolas en los cinco corregimientos de la ciudad de Medellín, utilizando modelos de Machine Learning(Universidad EAFIT, 2024) Gómez Arango, Alba Miriam; Valencia Diaz, Edison; Zuluaga Orrego, Juan FernandoIn a global context where agriculture and food production play a crucial role in food security, employment, and sustainability, this study focuses on predicting the yield of agricultural crops in the five districts of Medellín. The main objective is to design a prediction model for nine local crops using machine learning techniques. Medellín is distinguished by its diversity of crops, including peri-urban agriculture characterized by productive small plots distributed across various chagra-type crops. These traditional agricultural practices are carried out by an aging population of farmers. Accuracy in yield prediction becomes essential, as a significant portion of the production is dedicated to self-consumption, with a subsistence focus. However, surpluses are also traded, directly impacting the food security of the local community. The results highlight the effectiveness of machine learning models, particularly Boosting models such as PCA Random Forest and PCA XGB Boosting, in predicting the crops under study. These models demonstrate the ability to capture relationships between variables and the heterogeneity present in territorial production. However, opportunities for improvement related to reducing model errors have been identified, which can be addressed through continuous data collection and technical support provided to farmers. This will not only increase data availability but also contribute to refining the model and understanding performance behavior in the analyzed crops, facilitating decision-making in the agricultural sector of the municipality of Medellín. This project represents a valuable tool for professionals in the agricultural sector and institutions responsible for planning and agricultural development. It offers an innovative approach to sector data analysis, leveraging the advantages of data science. Through these techniques, opportunities are opened to establish strategies, plans, and projects that contribute to crop planning, the management of productive areas in the municipality, and the strengthening of local food security.Ítem A Robust Version of a Risk-Inverse Weighing Methodology for Portfolio Selection(Universidad EAFIT, 2024) Renza Chavarría, Juan Felipe; Ortiz Arias, SantiagoÍtem Predicting Infarct In-Hospital Mortality Using Machine Learning Supervised Models and Administrative Data for Colombia(Universidad EAFIT, 2023) Giraldo González, Sebastián; Posso Suárez, Christian Manuel; Gómez Toro, CatalinaÍtem Predicción de alteraciones nutricionales en función del índice peso para la talla en niños menores de 5 años, de la ciudad de Medellín(Universidad EAFIT, 2023) Bedoya Ríos, Santiago; Martínez Vargas, Juan David; Sepúlveda Cano, Lina María