Examinando por Materia "Boosting"

Mostrando 1 - 3 de 3
  • No hay miniatura disponible
    Publicación
    Control de la privacidad de la información en aplicaciones de teléfonos celulares
    (Universidad EAFIT, 2022) Arango Ramírez, María Camila; Muñetón Lopera, Andrés Felipe; Ramírez García, María Isabel; Echeverri Álvarez, Jonathan
  • No hay miniatura disponible
    Publicación
    Intervención comportamental en adultos mayores de Medellín para impulsar el pensamiento crítico ante la desinformación en WhatsApp sobre gestión de riesgos de desastres
    (Universidad EAFIT, 2025) Betancur Arboleda, Elizabeth; Mazo Barrientos, Juan Daniel
    Misinformation spread online is a global problem that requires local attention, especially when it is disseminated through instant messaging applications like WhatsApp, whose content cannot be externally curated. Disseminating this content is more challenging in the context of natural disasters and is influenced by emotional and cognitive frameworks, as well as the biases and heuristics present in everyday decision-making. Therefore, the behavior of spreading misinformation depends on each individual's capacity to manage what they decide to share. This thesis reports on a Boosting-type behavioral intervention at the individual level in older adults in the District of Medellín to encourage Critical Thinking in the face of misinformation on WhatsApp about disaster risk management and to assess whether it influences their intention to share misinformation. This intervention challenges the assumptions that older adults lose their critical thinking skills due to cognitive decline and aligns with studies that highlight the importance of believing in their abilities and strengthening them.
  • No hay miniatura disponible
    Publicación
    Modelo fundamental de crecimiento en utilidades y price-to-earnings ratio, P/E, de los índices accionarios internacionales
    (Universidad EAFIT, 2025) Jiménez Benítez, Daniel; Sandino Perdomo, Daniel; Navarrete Quintero, Nicolás; Diaz, Walter; Durango Gutiérrez, María Patricia
    The S&P500, a barometer of the U.S. economy, is one of the world's leading stock market indices. The price-to-earnings ratio (P/E) is a valuation measure that compares a stock's market price to its earnings per share, and is commonly used to assess whether stocks are overvalued or undervalued. Forecasting the P/E ratio is complex due to factors that can influence the ratio: interest rates, economic growth, market sentiment, and financial projections for companies, among others. In this research, two recurrent neural network models were implemented: LSTM (long short-term memory) and GRU (gated recurrent unit), as well as two machine learning models: XGBoost (extreme gradient boosting) and LigthGBM (light gradient boosting machine), to forecast the P/E ratio of the S&P500 using historical data between January 1990 and October 2024. The results show that all four models perform well, although the GRU model stands out in terms of accuracy and computational efficiency, without leaving aside the LightGBM model, a boosting algorithm, which also shows competitive results. The research offers valuable information on the use of the four models to forecast valuation ratios, and can be useful as support in investment decision making.