Examinando por Materia "ARIMA"
Mostrando 1 - 5 de 5
Resultados por página
Opciones de ordenación
Ítem 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, ÉdisonPublicación Desarrollo y comparación de modelos ARIMA-GARCH y SARIMA-GARCH para la estimación del tipo de cambio USD/COP y propuesta de coberturas cambiarias con derivados forward para empresa importadora de autopartes en Colombia(Universidad EAFIT, 2025) Caballero Rosas, Daniel; Molina Sierra, Luis FelipeThis research analyzed the estimation of the USD/COP exchange rate through the development and comparison of ARIMA-GARCH and SARIMA-GARCH models to design hedging strategies. Historical data from the Representative Market Rate (2019-2024) and optimization techniques in Python were used. Results indicated that SARIMA-GARCH provided higher predictive accuracy by capturing seasonal fluctuations and reducing errors compared to ARIMA-GARCH. Based on these forecasts, forward contract hedging strategies were proposed to mitigate exchange rate risk. However, market uncertainty and unexpected events may affect model accuracy, making recalibration every 60-90 days advisable. The combination of time series models with conditional heteroskedasticity proved essential in volatile markets, although its high computational demand can be a limitation. This study provides applicable tools for exchange rate risk management, optimizing financial decision making for importing companies.Ítem Methodological advances in artificial neural networks for time series forecasting(IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC, 2014-06-01) Cogollo, M. R.; Velasquez, J. D.; Universidad EAFIT. Escuela de Ciencias; Modelado MatemáticoObjective: The aim of this paper is to analyze the development of new forecasting models based on neural networks. Method: We used the systematic literature review method employing a manual search of papers published on new neural networks models in the time period 2000 to 2010. Results: Only 18 studies meet all the requirements of the inclusion criteria. Of these, only three proposals considered a neural networks model using a process different to the autoregressive. Conclusion: Although studies relating to the application of neural network models were frequently present, we find that the studies proposing new forecasting models based on neural networks with a theoretical support and a systematic procedure for the construction of model, were scarce in the time period 2000-2010. © 2012 IEEE.Publicación 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 Pronóstico de la inflación colombiana : una aproximación desde los modelos machine learning(Universidad EAFIT, 2022) Loaiza Zapata, José Fernando; Londoño Sierra, Liz Jeanneth; Riascos Salas, Jaime AndrésThe objective of this paper is to forecast monthly Colombian inflation based on its macroeconomic determinants. 7 machine learning models are used: linear regression, SMV, Decision Trees, MLP, KNN, SVR and LSTM, and 1 conventional ARIMA model. The models with the best prognosis were the ARIMA and the LSTM. Although, the prediction of the LSTM can be improved by making an optimal architecture of the data since it manages to capture the drastic changes of the variables, it could even be improved if the behavior of each of the divisions that make up the basic basket is included.