• español
    • English
  • Politics
  • English 
    • español
    • English
  • Login
View Item 
  •   Institutional Repository ULima
  • Tesis
  • Licenciatura
  • Ingeniería Industrial
  • Tesis
  • View Item
  •   Institutional Repository ULima
  • Tesis
  • Licenciatura
  • Ingeniería Industrial
  • Tesis
  • View Item
JavaScript is disabled for your browser. Some features of this site may not work without it.

Uso de Aprendizaje Automático para predecir la utilidad en la distribución de GLP en Lima Metropolitana

Thumbnail
View/Open
Tesis_Resumen
(application/pdf: 177.3Kb)
Autorización
(application/pdf: 255.2Kb)
Reporte de similitud
(application/pdf: 4.060Mb)
Date
2023
Author(s)
Vallejos Romero, Diego Adolfo
Deudor Fernandez, Christian Carlos
Advisor(s)
García López, Yván Jesús
Metadata
Show full item record
Abstract
The present descriptive quantitative research tries to find out which machine learning model is the most efficient to predict the utility of a bulk liquefied petroleum gas trading company in Metropolitan Lima. To determine daily profit, which will be a variable dependent on the output model. This dependent parameter has 5 independent variables and the highest correlation coefficient values. Within the independent parameters are sale price, quantity sold, purchase cost, transportation cost and kilometers traveled. There are several machine learning models, for this research the Artificial Neural Networks, Multiple Linear Regression and Random Forest models will be used, which estimated the utility through their own mathematical algorithms. To simulate the algorithms of the mentioned models, the Python program will be used. These models were trained for learning and validation of 70% and 30% of the database, that is, of the 235 data that were recruited, 165 data were used to calibrate and 70 data to validate. When making the comparison between the automatic learning models for the estimation of the daily utility of the trading company, the Random Forest model was obtained as the best option, obtaining an R2 of 0,959 and also having the lowest statistical error rates with respect to the models. of Artificial Neural Networks and Multiple Linear Regression.
URI
https://hdl.handle.net/20.500.12724/19430
How to cite
Vallejos Romero, D. A. & Deudor Fernandez, C. C. (2023). Uso de Aprendizaje Automático para predecir la utilidad en la distribución de GLP en Lima Metropolitana [Tesis para optar el Título Profesional de Ingeniero Industrial, Universidad de Lima]. Repositorio institucional de la Universidad de Lima. https://hdl.handle.net/20.500.12724/19430
Publisher
Universidad de Lima
Subject
Aprendizaje automático
Servicios del gas
Gas licuado de petróleo
Machine learning
Gas companies
Liquefied petroleum gas
Lima (Perú)
Collections
  • Tesis [1021]


Contact Us: [email protected]

Todos los derechos reservados. Diseñado por Chimera Software
 

 

Browse

All of RepositoryCommunities & CollectionsBy Issue DateAuthorsTitlesSubjectsAdvisorsAuthors UlimaDocument typeThis CollectionBy Issue DateAuthorsTitlesSubjectsAdvisorsAuthors UlimaDocument type

My Account

LoginRegister

Statistics

View Usage Statistics

Contact Us: [email protected]

Todos los derechos reservados. Diseñado por Chimera Software