Examinando por Materia "LSTM"
Mostrando 1 - 12 de 12
Resultados por página
Opciones de ordenación
Ítem Active portfolio management process with sentimental factor. Iterative deep learning approach(Universidad EAFIT, 2023) Alemán Muñoz, Julián Alberto; Pantoja Robayo, Javier OrlandoÍtem Comparación de modelos de series temporales ARIMA, SARIMAX y LSTM para la predicción del índice COLCAP(Universidad EAFIT, 2024) Osorio Aristizábal, David Santiago; Valencia Díaz, ÉdisonÍtem Currency Prediction : Stochastic hybrid diferencial equations with LSTM(Universidad EAFIT, 2024) Arbeláez Betancur, Hoover Arley; Marín Sánchez, Fredy HernánÍtem 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 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 Iterative Deep Learning Approach to Active Portfolio Management with Sentiment Factors(Springer, 2024-09-11) Pantoja Robayo, Javier Orlando; Alemán Muñoz, Julián Alberto; Tellez-Falla, Diego F.; Universidad EAFITWe suggest using deep learning networks to create expert opinions as part of an iterative active portfolio management process. These opinions would be based on posts from the X platform and the fundamentals of stocks listed in the S&P 500 index. Expert views are integral to active portfolio management, as proposed by Black–Litterman. The method we propose addresses the original subjectivity of the opinions by incorporating innovation and accuracy to generate views using analytical techniques. We utilize daily data from 2010 to 2022 for stocks from the S&P 500 and daily posts from Twitter API v2, collected under a research account license spanning the same period. We found that incorporating sentiment factors with machine learning techniques into the view generation process of the Black–Litterman model improves optimal portfolio allocation. Empirically, our results notably outperform the S&P 500 market when considering the annualized alpha.Ítem Machine learning model based on LSTM networks optimized with metaheuristic algorithms to predict cardholder churn(Universidad EAFIT, 2024) Correa Jaramillo, Diana Marcela; Aguilar Castro, José LisandroPublicación 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 PatriciaThe 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.Ítem Modelos de predicción estocástica para bitcoin : una evaluación de métodos y desempeño(Universidad EAFIT, 2023) Forero Criollo, Juan Sebastián; Hernández Hernández, Caroline; Cadavil Gil, AlejandroThis research focuses on forecasting Bitcoin (BTC) prices using statistical models, including LSTM, GRU, SVR, decision trees, Random Forest, and XGBoost. We evaluate their performance in terms of R2, RSME, MAPE, Lin Concordance Coefficient (CCC), and Explained Variance Score—metrics selected for their ability to assess regression models. We utilized BTC closing price data from 2014 to 2023, subjected to preprocessing involving cleaning, optimization, and data engineering. The models, initially unoptimized, were enhanced through hyperparameter tuning and specialized statistical techniques such as cross-validation, L1-L2 regularization, Bayesian and genetic optimization. The results highlight XGBoost as the optimal model with the incorporation of iterative hyperparameter tuning, Bayesian optimization, and nested cross-validation. It achieved outstanding values in all evaluated metrics: RSME of USD 30.45, MAPE of 0.09%, R-squared of 1.0, Lin Concordance Coefficient, and Explained Variance Score of 1.0 in each case.Ítem Predicción de rotación de empleados usando modelos de aprendizaje automático(Universidad EAFIT, 2023) Palacio Mesa, Luis Javier; Suárez Sierra, Biviana Marcela; Román Calderón, Juan PabloPublicación Predicción dinámica del valor del flete de mercado para vehículos 3s3 del puerto de Buenaventura a Bogotá : un modelo integrado con variables exógenas económicas y del sector logístico(Universidad EAFIT, 2025) Vélez Medina, Camilo Alejandro; García Vargas, Johan FelipeLogistics, especially road transportation as a fundamental part of the supply chain, directly impacts the costs and availability of products in cities. This project develops a predictive model to estimate the market value of freight transportation for 3S3-type vehicles from the port of Buenaventura, Colombia, to Bogotá, Colombia. The variable of interest, referred to as FP_mean, corresponds to the daily average freight production cost. The innovation of the model lies in its ability to integrate critical exogenous variables, such as Brent crude oil prices, the exchange rate of the dollar, sector-specific factors collected in the SICE TAC (fuel, tolls, tires, lubricants, filters, maintenance, personnel), RNDC (National Road Cargo Dispatch Registry), and the arrival of ships at the port with their respective types of cargo. Multiple advanced modeling approaches were evaluated, including ARIMA, SARIMA, Random Forest, and LSTM, with the Random Forest model incorporating exogenous variables (random_forest_exogen) standing out for its superior performance, achieving an RMSE of 211,395.42 and a MAPE of 3.20%, making it the most accurate for estimating FP_mean. Additionally, the LSTM and SARIMA models also demonstrated competitive results, striking a balance between accuracy and stability across various scenarios. These findings highlight the importance of combining advanced machine learning techniques with domain expertise in logistics.Ítem Red asociativa usando LSTM para la predicción diaria de apertura y cierres de índices bursátiles(Universidad EAFIT, 2022) Mejía Uribe, Simón Pedro José; Laniado, Henry; Almonacid Hurtado, Paula María