Maestría en Ciencias de los Datos y Analítica (tesis)
URI permanente para esta colección
Examinar
Examinando Maestría en Ciencias de los Datos y Analítica (tesis) por Fecha de publicación
Mostrando 1 - 20 de 139
Resultados por página
Opciones de ordenación
Ítem Modelo matemático combinado para la clasificación de neuroimágenes basado en medidas de similaridad entre hemisferios del cerebro(Universidad EAFIT, 2020) Cardona Pineda, Danny Styvens; Laniado Rodas, HenryThe main contribution of this work is the combination of similarity measures, methods for the construction of subspaces and classification models. Specifically, the NCC was used as a measure of similarity, which was projected to subspace in singular value decomposition following the Eigenfaces methodology, to then apply classification models on these projections. Results with an accuracy of 81% and a predictive capacity of at least 79% were observed for this combination of methods.Ítem Hacia un método de predicción de resultados de evaluación en un contexto de micro aprendizaje(Universidad EAFIT, 2020) Sánchez Castrillón, Jose David; Vallejo, Paola; Tabares Betancur, Marta Silvia; Tabares Betancur, Marta SilviaThis paper presents a method for predicting the evaluation results of learners interacting with a context-aware microlearning system. We use ASUM-DM to guide di erent data analytics tasks, including applying a genetic algorithm that selects the prediction's highest weight features. Then, we apply machine learning models like Random Forest, Gradient Boosting Tree, Decision Tree, SVM, and Neural Networks to train data and evaluate the context's e ects, either success or failure of the learner's evaluation. We are interested in nding the model of signi cant context-in uence to the learner's evaluation results. The Random Forest model provided an accuracy of 94%, which was calculated with the cross-validation technique. Thus, it is possible to conclude that the model can accurately predict the evaluation result and relate it with the learner context. The model result is a useful insight for sending noti cations to the learners to improve the learning process. We want to provide recommendations about learner behavior and context and adapt the microlearning content in the future.Ítem Constructing Black Litterman optimal portfolios based on Wilcoxon test(Universidad EAFIT, 2020) Graciano Londoño, Mateo; Laniado Rojas, Henry; Laniado Rodas, HenryÍtem Predicting the entrepreneurial process phases : a machine learning approach(Universidad EAFIT, 2021) Ceballos Arias, Juan Camilo; Álvarez Barrera, Claudia Patricia; Almonacid Hurtado, Paula MaríaÍtem Graffiti and government in smart cities : a deep learning approach applied to Medellín city, Colombia(Universidad EAFIT, 2021) Rozo Alzate, Javier Arturo; Vallejo Correa, Paola Andrea; Tabares Betancur, Marta Silvia; Tabares Betancur, Marta SilviaÍtem ROC-ME reconocimiento óptico de caracteres en medidores de energía(Universidad EAFIT, 2021) Mejía Quintero, Camila; Quintero Montoya, Olga LucíaÍtem Diseño de un modelo de decisión para la retención del capital humano en el sector Business Process Outsourcing (Bpo) : el caso de Konecta-Colombia(Universidad EAFIT, 2021) Muñoz Mora, Cristian David; Muñoz Mora, Juan CarlosÍtem Forecasting stock return using a recurrent neural network apply to a financial optimization problem(Universidad EAFIT, 2021) Ochoa Ramírez, Juliana; Almonacid Hurtado, Paula MariaThis paper presents a methodological proposal for optimizing financial asset portfolios by incorporating the returns predictions instead of the historical returns to calculate an efficient frontier. We changed the return means methodology to forecast by the return with LSTM neural network. We performed several simulation exercises to evaluate the methodology with real data from the US stock market to examine our portfolio optimization model. To evaluate our results, we compared the mean-variance frontier efficiency with the neural network return model. We selected one optimal portfolio that offered the highest expected return for a defined level of risk and compare both models. We show how the neural network return model has a better performance for different periods of time, outperforming the mean-variance model at the same level.Ítem Sistemas de recomendación contextual(Universidad EAFIT, 2021) Franco Zapata, Andrés; Zuluaga Suarez, Daniel; Tabares Betancur, Marta Silvia del SocorroÍtem Análisis y predicción de recontactos en un contact center(Universidad EAFIT, 2021) Velásquez Gaviria, Diana Catalina; Quintero Montoya, Olga LucíaThe main purpose of this work is to solve in a methodical and formal way, making use of ma- chine learning models, a real problem of the productive sector that allows in addition to adding value for decision making, to provide a methodology and a compact, simple and reliable model that can be deployed and put into production in the technological platform that supports the call handling of a contact center so that benefits can be generated in the provision of the service for different sectors, generating efficiencies in the use of the channel and maximizing the customer experience in the attention of their requirements. To achieve this purpose, an airline dataset was taken containing the detail of all historical calls made by customers to a contact center during a period of 7 months (February to August 2019) and information associated with the performance of the agents handling those calls in order to predict whether users will generate at least one recontact to the contact center for the attention of their requirements before three days with respect to their initial contact. The methodology used was focused on making an ap- propriate selection of features and choosing a machine learning model that generates optimal results and enables an easy implementation allowing to identify in real time those customers with high probabilities of recontacting so that a strategy can be developed with them to impro- ve their experience. It was found that with 7 variables associated with the historical behavior of customers in the use of the channel such as frequency of calls (amount), average duration, number of agents who have served the customer (agents), time elapsed between first and last call (validity), number of days per month in which calls are made (AverageDaysInMonth), ave- rage number of calls per day (Average-Day) and time elapsed since the customer’s last call to the cut-off date of the analysis (Recency), it is possible to predict with a simple model and with very good results (AUC=88.9 %) whether a customer will call the contact center again.Ítem Metodología enfocada a la identificación de oportunidades de inversión en el mercado inmobiliario(Universidad EAFIT, 2021) Ríos Ruiz, Obed; Laniado Rodas, Henry; Montoya López, AndrésÍtem Predicción de precios de tres tipos de contratos de energía con modelos de aprendizaje de máquinas, metodología CRISP-DM(Universidad EAFIT, 2021) Aristizábal Toro, Santiago; Toro Bermúdez, MauricioÍtem Detección de puntos y tiempos de robo de información de tarjetas de crédito en comercio electrónico(Universidad EAFIT, 2021) Velásquez Moná, Karen Lizeth; Almonacid Hurtado, Paula María; García Cruz, Ehidy Karime; López Rojas, EdgarÍtem Ensemble of temporal convolutional and long short-term memory neural networks apply to forecasting USDCOP exchange rate(Universidad EAFIT, 2021) Torres Marulanda, Juan Esteban; Almonacid Hurtado, Paula MaríaThis paper applies a neural network with ensemble of temporal convolutional network (TCN) and long short-term memory (LSTM) layers approach to forecast foreign exchange rates between the US dollar (USD) and Colombian Peso (COP) and obtain a better performance. This study provides evidence on the TCN and LSTM neural network model’s effectiveness and efficiency in forecasting temporal series. It should contribute positively to developing theory, methodology, and practice of using an artificial neural network to develop a forecasting model for financial temporal series.Ítem Reconocimiento multimodal de emociones de estudiantes orientado a ambientes virtuales de aprendizaje(Universidad EAFIT, 2021) Henao Salazar, Juan Camilo; Montoya Múnera, Edwin Nelson; Aguilar Castro, José LisandroÍtem GRILLA: Grouping Recall Least Lazy Algorithm. Modelo matemático para cobranza selectiva usando técnicas de aprendizaje automático(Universidad EAFIT, 2021) Moreno Zapata, Juan Sevastian; Quintero Montoya, Olga LucíaÍtem Análisis de quiebra empresarial ante escenarios de contracción de la oferta y la demanda ocasionados por el Covid-19 : un estudio del sector comercio colombiano(Universidad EAFIT, 2021) Urán González, Ana María; Arjona, MateoÍtem Estimación de precio de oferta para una planta hidroeléctrica de baja regulación en la bolsa de energía(Universidad EAFIT, 2021) Mosquera Galvis, Liceth Cristina; Quintero Montoya,Olga LuciaÍtem Hybrid algorithm based on Reinforcement Learning and DDMRP methodology for inventory management(Universidad EAFIT, 2021) Cuartas Murillo, Carlos Andrés; Aguilar, José Lisandro; Aguilar, José LisandroThis article proposes a hybrid algorithm based on Reinforcement Learning and on the inventory management methodology called DDMRP (Demand Driven Material Requirement Planning) to determine the optimal time to buy a certain product, and how much quantity should be requested. For this, the inventory management problem is formulated as a Markov Decision Process where the environment with which the system interacts is designed from the concepts raised in the DDMRP methodology, and through the Reinforcement Learning algorithm – specifically, Q-Learning. The optimal policy is determined for making decisions about when and how much to buy. To determine the optimal policy, three approaches are proposed for the reward function: the first one is based on inventory levels; the second is an optimization function based on the distance of the inventory to its optimal level, and the third is a shaping function based on levels and distances to the optimal inventory. The results show that the proposed algorithm has promising results in scenarios with different characteristics, performing adequately in difficult case studies with a diversity of situations such as scenarios with discontinuous or continuous demand, seasonal and non-seasonal behavior with high demand peaks, multiple lead times, among others.Ítem Supervivencia de las nuevas empresas : una aproximación desde el Machine Learning(Universidad EAFIT, 2021) Román Ramírez, Daniel; Valencia Diaz, EdwinEntrepreneurship is starting a search for the generation of value, through the creation or expansion of an economic activity, through the identification and exploitation of new products, processes and markets. The generation of ventures depends on the integrated ecosystem, which includes personal aspects of individuals, market conditions, access to financial resources, public policies through programs and projects that favor business formation. In Colombia, the statistics of recent years show an exponential growth in the creation of new companies, however, more than 50% of them do not reach 5 years of life. The numbers of business failure have not decreased, exposing the weakness of governments on the issue of expanding economic development. To achieve the increase in productivity and the expansion of the base of the economy, it is necessary to understand the challenges that entrepreneurs face for the survival of the company, in addition, thanks to the boom that the use of of Machine Learning techniques and information management, models based on supervised learning and Cox Regression will be applied to understand the important characteristics of the entrepreneur and the business that could affect stability in the market and based on this estimate the probability of survival, in its first years of constitution. The methodology to be applied is based on classification models. Finally, with the results of the survival model, it is expected to be a useful support for entrepreneurs by providing information for making business decisions.