Examinando por Materia "LightGBM"

Mostrando 1 - 4 de 4
  • No hay miniatura disponible
    Publicación
    Análisis predictivo de la deserción laboral en BPO : aplicaciones avanzadas de Machine Learning
    (Universidad EAFIT, 2023) Castelblanco Benítez, Julián; Almonacid Hurtado, Paula Maria
  • 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.
  • No hay miniatura disponible
    Publicación
    Predicción de direcciones de activos financieros basados en la volatilidad en series temporales utilizando machine learning
    (Universidad EAFIT, 2026-02-24) Holguín Carvalho, Mateo; Velasco Vera, Henry Giovanny
    Identifying effective trading signals in financial assets is a challenge that draws attention across multiple disciplines due to the volatile and dynamic nature of financial markets. The complexity investors face stems from the wide range of factors that influence asset prices, including macroeconomic variables, corporate decisions, and unexpected events, making it difficult to obtain precise estimates of future movements. This is particularly relevant for investors seeking to build portfolios that maximize returns. In this context, some variables exhibit stronger relationships with market-driven factors, making them useful indicators for anticipating price direction. Nevertheless, recent advances in computing and in Machine Learning and Deep Learning techniques have enabled the development of more sophisticated models that facilitate this task. This study compares time-series-based machine learning methodologies, specifically LSTM neural networks and LightGBM decision-tree models, while incorporating Conditional Heteroskedasticity models (GARCH) to improve the classification of buy and sell signals in financial instruments, accounting for both historical patterns and external variables affecting asset behavior. The results show that LightGBM achieved the best predictive performance, with notable metrics such as an F1 Score of 0.823 and an AUC-ROC of 0.923 in validation, whereas LSTM delivered the best financial performance, reaching a cumulative return of 28.05% and a Sharpe Ratio of 0.70, clearly outperforming a Buy-and-Hold strategy. These findings suggest that although daily directional prediction is inherently complex, advanced Machine Learning models can transform weak signals into profitable trading strategies.
  • No hay miniatura disponible
    Publicación
    Predicción del precio óptimo de compra de sacos de papel en la industria cementera : un enfoque basado en modelos SARIMAX, ARIMA y red neuronal LSTM
    (Universidad EAFIT, 2025-12-09) Morales Martínez, Andrés Felipe; Fonseca Valero, Diego Fernando
    This research addresses the problem of forecasting the purchase price of kraft paper sacks in the Colombian cement industry, within a context characterized by high price uncertainty and the absence of financial hedging instruments. Using internal transactional data extracted from the ERP system for the 2014–2023 period, together with public exogenous variables such as the exchange rate (TRM) and stock prices of global suppliers in the paper industry, a reproducible dataset was built for purchase price forecasting. The study compared the performance of four time-series approaches: ARIMA, SARIMAX, LSTM, and LightGBM, under a 90/10 temporal validation protocol and strict control of information leakage. As a central part of the methodology, a daily time series was reconstructed using the LOCF technique, and feature engineering was incorporated to better represent the stepwise nature of the price series. The results show that linear models and the LSTM applied to the original series produced high forecasting errors, whereas the best performance was achieved by nonlinear models applied to the transformed series. In particular, the LSTM with the transformed daily series achieved the best overall result (MAE = 4.57 COP), followed by LightGBM (MAE = 8.03 COP), clearly outperforming ARIMA and SARIMAX. It is concluded that an adequate representation of the time series is as important as the selection of the predictive model, and that the combination of internal data, exogenous variables, and nonlinear methods can generate useful operational signals to support more timely, objective, and data-driven purchasing decisions in industrial sourcing contexts.