Repositorio Institucional Universidad EAFIT ::Examinando por Materia "Machine Learning"

Examinando por Materia "Machine Learning"

Mostrando 1 - 20 de 51

Análisis comparativo de modelos predictivos para la estimación de PM2.5 : un enfoque basado en aprendizaje automático y predicción conformal
(Universidad EAFIT, 2024) Camelo Valera, Matías; Martínez Vargas, Juan David; Sepúlveda Cano, Lina Maria
Fine particulate matter (𝑃𝑀2.5pollution poses a significant environmental and public health challenge, requiring accurate predictive models for its monitoring and control. This study compares different machine learning approaches, including Linear Regression, Random Forest, and XGBoost, with and without the inclusion of mobility variables, to estimate 𝑃𝑀2.5 levels. Additionally, inductive conformal prediction is implemented to quantify uncertainty in the estimates and provide confidence intervals with 𝛼=0.05. The results show that while XGBoost experiences performance deterioration during training when mobility variables are included, it achieves the best validation performance with the lowest mean absolute error and the highest coefficient of determination. Conformal prediction enabled the establishment of confidence intervals with 89.26% coverage, close to the expected 95%, ensuring model reliability across different spatial and temporal scenarios. In conclusion, the use of machine learning models combined with advanced validation and calibration techniques, such as conformal prediction, enhances the accuracy and reliability of 𝑃𝑀2.5 estimation. However, the quality of input variables, particularly mobility-related data, remains a challenge, highlighting the need to incorporate meteorological information and improve data resolution. These findings contribute to the development of more reliable predictive tools for environmental management and air quality policy decision-making.
Análisis de los resultados de la aplicación del instrumento para la evaluación docente de la universidad EAFIT
(Universidad EAFIT, 2024) Fernández Carmona, Laura Catalina; Guarín Zapata, Nicolás; Mola Ávila, José Antonio
Análisis predictivo del riesgo de default en microcrédito un enfoque de machine learning en sector financiero
(Universidad EAFIT, 2024) Mendoza Trillos, Laura; Suárez Sierra, Biviana Marcela
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 Andrea
Analítica de datos aplicada a la cobranza de cartera
(Universidad EAFIT, 2019) Montoya Yepes, Juan David; Parra Giraldo, Diana Carolina
In order to improve the portfolio collection work performed daily at Cobroactivo LLC, it was decided to use the data stored in this company to optimize its processes. To do this, it was necessary to implement data analytics models, creating a Big Data environment that would allow efficient access to information through a Data Warehouse, as well as some tools to make an exploratory analysis of the existing data and evaluate the weak pointsthat must be improved when managing users. Warehouse, as well as some tools to make an exploratory analysis of the existing data and evaluate the weak points that must be improved when managing users. Likewise, three Machine Learning models were developed in charge of debugging the debtors, predicting the payment probabilities and optimally recommending which advisor should be assigned to each debtor and which is the appropriate contact channel for him / her. Finally, two web applications were developed. The first allows the monitoring of the company's internal processes by automating repetitive processes and decreasing their execution time from weeks o seconds; the second allows the monitoring of collection work by customers and banks, thereby offering added value.
Aplicación de modelos predictivos tradicionales y de machine learning para evaluar la insolvencia en el sector salud de Colombia
(Universidad EAFIT, 2025) Girón Ocampo, César Eduardo; Mercado Vargas, Luis Fernando; Cruz Castañeda, Vivian; Álvarez Franco, Pilar Beatriz
Aprendizaje reforzado profundo para la administración de portafolios de renta fija
(Universidad EAFIT, 2023) Mejía Estrada, David; Almonacid Hurtado, Paula María
This paper applies deep reinforced learning techniques to the management of fixed income investment portfolios, specifically sovereign securities issued by the Colombian government. The period of analysis covers seven years, from January 2015 to December 2022. We find that it is possible to generate profitability and achieve efficient risk management because of the trading strategies that deep reinforced learning models foresee more convenient given certain market conditions and of each of the securities, such as their implied risk in metrics like DV01, Duration and Convexity. Finally, this study contributes to the field of machine learning and artificial intelligence applications on investment portfolio management, with a relatively new focus on the fixed income market in general, consolidating itself as one of the first works to apply reinforcement learning techniques to the Colombian public debt market.
Automatic Electrical Meter Forecasting : a Benchmarking Between Quantum Machine Learning and Classical Machine learning
(Universidad EAFIT, 2024) Montes Castro, Jonathan Javier; Lalinde Pulido, Juan Guillermo; Sosa-Sierra, Daniel
This work benchmarks Quantum Long Short-Term Memory (QLSTM) against classical LSTM networks using electrical meter data (KWh) from EPM, a public utility company, clients. The results show that QLSTM models learn in half the epochs compared to LSTM, as measured by the MSE cost function, while maintaining strong performance with respect to bias (Mean Absolute Percentage Error, MAPE) and variance (R^2) metrics. QLSTM leverages variational quantum circuits (VQC) to replace traditional LSTM cell gates, demonstrating the potential of quantum-hybrid algorithms in forecasting tasks. This study highlights the efficiency and accuracy advantages of quantum machine learning applied to real-world data from EPM’s electrical metering services.
Characterization of Phytosanitary Risks in Agricultural Crops using Multispectral Images
(Universidad EAFIT, 2025) García Montenegro, Michell; Peña Palacio, Juan Alejandro; Martínez Vargas, Juan David
Comparación de métodos de aprendizaje de máquina en el análisis de series temporales para la predicción de tasas de cambio
(Universidad EAFIT, 2025) Restrepo Vallejo, Stevens; Almonacid Hurtado, Paula María
The study of global financial markets represents a complex field of research, characterized by high competitiveness and volatility. The analysis of exchange rates serves as a focal point for investors and firms aiming to maximize profitability while minimizing risks. Although various techniques currently exist for estimating exchange rate price changes, the inherent stochastic nature of the market, coupled with the influence of political-economic factors, continues to pose significant challenges for precise and reliable data analysis. This study addresses the prediction of the prices of some of the most significant exchange rates in this market. Machine learning methods, which have demonstrated outstanding performance in the literature on time series forecasting, are compared and evaluated against a baseline linear model. The study primarily employs Random Forest models, Long Short-Term Memory (LSTM) neural networks, and a hybrid model combining Convolutional Neural Networks (CNNs) with LSTMs. Additionally, the robustness of these models is explored in the presence of outliers, with the aim of mitigating the risks associated with predictions involving highly variable data behaviors. The goal is to develop an adaptable analytical framework that enables investors and financial analysts to anticipate market movements, thereby enhancing their ability to make data-driven, informed decisions.
Contrato de prestación de servicios jurídicos por parte de la Inteligencia Artificial en Colombia : viabilidad, caracterización y particularidades
(Universidad EAFIT, 2024) Soto Mejía, José Juan; Sánchez Daniels, Catalina del Pilar
Deep Learning como alternativa en la predicción del precio de las acciones del mercado de valores colombiano
(Universidad EAFIT, 2021) Uribe Ramírez, Sebastián; Almonacid Hurtado, Paula María
Desarrollo de librería para manejo de redes neuronales en Java para tecnofactor
(Universidad EAFIT, 2019) Arboleda Echeverry, Juan Camilo; Rincón Bermúdez, Rafael David
The aim of the present project is to design and develop a working library that enables the creation and adaptation of Neural Networks, defined in a way that is simple to use by Java developers. The developed library will be used to design and obtain a neural network capable of recognizing handwritten digits, from the MNIST database.
Detección automática de acordes empleando técnicas de caracterización de audio y machine learning
(Universidad EAFIT, 2025) Gil Urrego, Rafael Alejandro; Martínez Vargas, Juan David; Sepúlveda Cano, Lina María
Automatic chord detection in audio tracks is essential for developing various musical applications, such as music transcription and score generation. For this reason, there has been a growing interest in the field of data science to explore different strategies to address this need. The main approach studied in recent years is based on extracting features from audio files that contain chord information. Transforming the audio signal using different frequency analysis tools has generated data with a greater ability to describe the musical components present in the processed audio track. The Mel spectrogram and the Chromagram are some of the methods used for these tasks. Additionally, classical supervised analytical models such as Support Vector Machines (SVM), Random Forest, and Convolutional Neural Networks (CNN) have been employed in several studies. These models have demonstrated a high level of accuracy in chord identification. However, in most cases, they have been limited by the number of chord classes to estimate, as an increase in the number of classes can confuse the system, typically allowing a maximum of 24. In this thesis, a system for automatic chord identification was developed by implementing different classical and modern analytical models. For audio feature extraction, the pre-trained models HuBERT and VGGish were used. These extracted features were then fed into three classical models—SVM, Random Forest, and Gradient Boosting—to compare their results with those obtained by a modern model. The HuBERT architecture was chosen as the modern baseline model since it can function both as a feature extractor and a classifier. The experiments were conducted using recordings of 48 different chord classes, all played on a digital piano, providing a solid dataset for training and evaluating the proposed system’s performance. The study confirmed previous research findings: to obtain accurate chord class estimations, it is crucial to improve the characterization techniques of the input audio recordings. A recurring issue identified was the lack of a detailed description of the musical components in the recordings, which affected the models’ ability to deliver optimal results. Our findings highlight that precise feature extraction is key to reducing model generalization error, enabling better chord class identification in both classical supervised approaches and modern architectures such as HuBERT. Finally, it is concluded that modern models, including those based on Transformers, have a high dependency on the quantity and diversity of the data. To achieve effective adaptability, the training data must exhibit sufficient variations within the same class. When data lack intra-class variability, these systems struggle to adapt to new recordings, especially those with background noise or distortions.
Diseño y evaluación de un score de riesgo crediticio. Evidencia para una empresa comercializadora en Colombia
(Universidad EAFIT, 2024) Matiz Ruiz , John Jairo; Cruz Castañeda, Vivian; Álvarez, Pilar
Electric Vehicle monitoring system : analysis of driving patterns and their influence on battery degradation
(Universidad EAFIT, 2022) Echavarría Correa, Santiago; Mejía Gutiérrez, Ricardo; Montoya, Jose Alejandro
Equidad algorítmica : un estudio aplicado al mercado hipotecario de los Estados Unidos
(Universidad EAFIT, 2024) Montoya Mesa, Ana María; Cruz Castañeda, Vivian; Álvarez Franco, Pilar
Estimación del crecimiento poblacional de Leptopharsa Gibbicarina en palma de aceite (caso de estudio)
(Universidad EAFIT, 2025) Salazar Hoyos, Alejandro; Restrepo Arias, Juan Felipe
Estrategias de trading en acciones de BVC basadas en Machine Learning. ¿Precisión implica desempeño?
(Universidad EAFIT, 2022) Cerro Espinal, Carlos Alberto; Agudelo Rueda, Diego Alonso
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 María
In 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.

Examinando por Materia "Machine Learning"

Resultados por página

Opciones de ordenación