REVISTA DYNA NEW TECHNOLOGIES

Key words:

Aprendizaje automático, redes neuronales artificiales, regresión lineal múltiple, Bosque Aleatorio y modelos predictivos, Machine learning, artificial neural networks, multiple linear regression, Random Forest and predictive models.

Article type:

COLABORACION/COLLABORATION DAMR

Section:

COLLABORATIONS

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 five independent variables: sale price, quantity sold, purchase cost, transportation cost and kilometers traveled, as well as the values with the highest correlation coefficients.
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 was used. These models were trained to learn and validate 70% and 30% of the database, that is, of the 235 data collected, 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.
Keywords: Machine learning, artificial neural networks, multiple linear regression, Random Forest and predictive models.