Maestría en Ciencias de los Datos y Analítica (tesis)
URI permanente para esta colección
Examinar
Envíos recientes
Ítem Metodología analítica para la estrategia de precios en pymes : una aplicación en el sector automotriz(Universidad EAFIT, 2024) Álvarez Restrepo, Victoria; Saldarriaga Aristizábal, Pablo AndrésÍtem Predicción de deserción de clientes en el mercado de seguros de transporte de carga en Estados Unidos mediante técnicas de Machine Learning : un caso de estudio(Universidad EAFIT, 2024) Uribe Durango, Víctor Ricardo; Almonacid Hurtado, Paula MaríaÍtem Sistema de reconocimiento de placas colombianas por medio de redes convolucionales para acceso a áreas residenciales(Universidad EAFIT, 2024) Pinto Restrepo, Daniel Enrique; Olarte Hernández, TomásÍtem Portfolio Optimization Using Predictive Auxiliary Classifier Generative Adversarial Networks : Application to the Colombian stock market(Universidad EAFIT, 2024) Arango López, Federico; Castellanos Ríos, SantiagoÍtem Estudio de la relación entre los valores sociales y la aceptación de sobornos como conducta corrupta : un estudio con modelos SEM y datos de la encuesta mundial de valores(Universidad EAFIT, 2024) Gómez Convers, Giovanny Hernando; Castrillón-Orrego, Sergio A.; Almonacid Hurtado, Paula MaríaIn a global context of rapid social change, investigating the relationship between social values and corruption has become increasingly urgent and significant. Which behaviors are desirable? Which do we manifest in daily life? The World Values Survey (WVS) serves as a crucial data source for understanding social values in various contexts. However, how these values influence the acceptance of bribery, and thus corruption, has not been sufficiently explored. This study examines the underlying patterns in response clusters and systematically analyzes them using the holistic possibilities offered by the institutionalism theoretical framework. The objective is to identify the most significant causalities and influences in the relationship between social values and corruption. Through robust data analysis, imputation techniques, dimensionality reduction, clustering analysis, and SEM modeling, we identify the main factors impacting the acceptance of bribery. The results demonstrate that the three pillars of institutionalism provide a valuable approach to understanding corruption by simultaneously considering key variables and components. When internalized, social values facilitate the acceptance of bribery in certain contexts, highlighting the influence of the cognitive dimension. Although legal frameworks can enhance transparency, cultural environment and customs have a more determining influence on the acceptance of corrupt practices. These findings underscore the need to foster a strong ethical culture and implement educational programs that promote integrity and transparency to effectively mitigate corruption.Ítem Modelo predictivo de insolvencia empresarial para las pymes en Colombia(Universidad EAFIT, 2024) Castro Espitia, Camilo; Martínez Vargas, Juan David; Sepúlveda Cano, Lina MaríaBusiness insolvency has an economic impact on the affected company and, directly and indirectly, on its suppliers of goods and services. This ends up affecting the general population, who are the consumers of these goods and services. Therefore, it is important to analyze and study the possible factors that lead a company to enter a situation of economic insolvency. In accordance with the above, the objective of this work is to predict business insolvency in the Colombian context for SMEs. Likewise, use will be made of the financial data available from the Superintendency of Companies in the year 2021 and the companies that entered into a situation of economic insolvency in the year 2023. In this way, through financial indicators, it will be possible to construct the explanatory variables. of economic insolvency and achieve a predictive model of economic insolvency. This work is approached as follows: first, information is extracted from the Superintendency of Companies for SMEs in 2021 and companies that entered economic insolvency in 2023 to obtain our objective variable. Then, based on the data obtained, the financial ratios necessary for this study are calculated, using the financial statements of these companies corresponding to the year 2021. Next, the exploratory data analysis is carried out to obtain a broader knowledge of the set. of data and analyze correlation issues between variables, among other aspects. Finally, several machine learning models are designed to determine which one is most appropriate for the case studyÍtem Comparativa de modelos para el reconocimiento de estructuras de datos tabulares : un enfoque desde el aprendizaje profundo(Universidad EAFIT, 2024) Garzón Vargas, José Miguel; Martínez Vargas, Juan David; Sepúlveda Cano, Lina MaríaÍtem Stock Market Forecasting : Comparing Machine Learning and Deep Learning with Risk-Return Model Selection and Evaluation in a Walk-forward Approach(Universidad EAFIT, 2024) Castro Marín, Carlos Andrés; Olarte Hernández, Tomás; Olarte Hernández, TomásThis study compares the effectiveness of machine learning and deep learning algorithms in forecasting stock market direction using daily market data of Apple Inc. stock. We aim to determine if these algorithms can identify repeatable patterns across time using price and volume history and assess which are most capable. To ensure robustness, we employ a walk-forward validation approach to maintain the temporal dimension of the data and simulate real trading conditions. This method allows us to test models across different market conditions and measure their predictive power. We prioritize model selection and evaluation based on financial return and risk metrics, focusing on profitability rather than traditional machine learning performance metrics, which often do not correlate with financial outcomes. Our findings show that traditional machine learning algorithms, specifically Random Forest, outperform deep learning models under the selected asset and conditions tested. Machine learning models exceed the stock benchmark regarding Sharpe ratio, while deep learning models struggle to manage risk effectively, leading to poorer performance. This discrepancy is likely due to the complex solution space deep learning algorithms navigate to optimize and the amount of data required by these models. However, we hypothesize that the latter could improve its performance if tested with different architectures and hyperparameters, including newly developed transformer attention-based architectures and models such as TimeGPT and others, shown in the related work section.Ítem Aplicaciones de NLP y modelos de atención para la identificación de estrés en textos de redes sociales(Universidad EAFIT, 2024) Moya Ortiz, Francisco Javier; Hernández Torres, SantiagoÍtem Non-parametric and Robust Multivariate Projection Control Charts Based on Extreme Kurtosis and Skewness Directions(Universidad EAFIT, 2024) Caicedo Jiménez, Luis Miguel; Ortiz Arias, SantiagoÍtem A Dynamic Approach to Modeling Count Data Based on Intensity Functions of Non-Homogeneous Poisson Processes and Functional Data Techniques(Universidad EAFIT, 2024) Chavarría Serna, Juan Esteban; Ortiz Arias, Santiago; Velasco, HenryÍtem Medición no invasiva de CSAT mediante técnicas de procesamiento de lenguaje natural(Universidad EAFIT, 2024) Zapata Castaño, Jonathan Stiven; Monsalve Aristizabal, Juan Daniel; Ortiz Arias, SantiagoÍtem Modelo de estimación analítica de liquidez en instituciones financieras(Universidad EAFIT, 2024) Rentería Roa, Jorge Luis; Ortiz Arias, SantiagoÍtem Análisis de discurso de los máximos responsables de las empresas participantes en el COLCAP(Universidad EAFIT, 2024) Cuervo Garcia, Dairo Alberto; Pantoja Robayo, Javier Orlando; Ceballos Cañón, Johan ArmandoÍtem Equidad algorítmica : un estudio aplicado al mercado hipotecario de los Estados Unidos(Universidad EAFIT, 2024) Montoya Mesa, Ana María; Cruz Castañeda, Vivian; Álvarez Franco, PilarÍtem Predicción de fallas en estaciones base de una red de telefonía móvil(Universidad EAFIT, 2024) Londoño Parra, Luis Felipe; Montoya Múnera, Edwin NelsonÍtem Aplicación de métodos de visión artificial para la detección de huevos en una planta de producción avícola(Universidad EAFIT, 2024) Cardona Ortiz, César Augusto; Ortiz Arias, SantiagoÍtem Integración de MLOps en la administración de riesgo de modelos : un enfoque innovador para la fiabilidad y robustez en modelos predictivos(Universidad EAFIT, 2024) Castañeda Ríos, José Luis; Ospina Arango, Juan DavidÍtem Integración de estimadores robustos y no-paramétricos de dispersión en el clasificador LDA para monitoreo de riesgo crediticio(Universidad EAFIT, 2024) Arcia Hernández, Jesús Alberto; Ortiz Arias, SantiagoÍtem Predicción de precios del sector inmobiliario en zonas costeras del Atlántico en EE.UU., mediante el uso de técnicas de Machine Learning(Universidad EAFIT, 2024) Gallego Muñoz, Sara; Almonacid Hurtado, Paula MaríaThe real estate sector is fundamental to economies, representing a significant percentage of GDP in the economies of developed and emerging countries. This market involves key players such as investors, buyers, financial entities and government institutions, who require accurate forecasts on real estate median prices to adjust strategies, policies and make informed decisions. In recent years, methodologies have been proposed to estimate the price of real estate in central urban cities, using variables associated with the property description and geographic location. In this paper we propose a methodology to predict the median price of real estate in Atlantic coastal areas in the U.S., using variables related to both the property and its environment and the application of Machine Learning and Deep Learning techniques. It is expected to obtain the prediction of the price of real estate for Atlantic coastal areas in the U.S., for which this valuation is not usually obtained in a public and reliable way.