A Predictive Sales System Based on Deep Learning DOI Open Access

Jean Paul Luyo Ballena,

Cristhian Pool Ortiz Pallihuanca,

Ernesto Adolfo Carrera-Salas

и другие.

International Journal of Advanced Computer Science and Applications, Год журнала: 2024, Номер 15(1)

Опубликована: Янв. 1, 2024

There are several techniques for predictive sales systems, in this study, a system based on different machine learning algorithms is developed trading company Lima. As any company, it needs to be accurate its calculations manage the volume of production or product purchases. With system, has mechanism order products from supplier predictions and estimates according projection sales. For Deep Learning technology neural network architectures GRU (Gated Recurrent Unit), LSTM (Long Short Term Memory) RNN (Recurrent Neural Network) were used, 10 sampled, quantities last 12 months obtained evaluation. The study found that architecture excels accuracy, significantly outperforming terms Mean Absolute Percentage Error (MAPE), achieving an average MAPE 7.07%, contrast 27.14% 36.17% RNN. These findings support effectiveness versatility time series prediction, demonstrating usefulness variety real-world applications.

Язык: Английский

A Predictive Sales System Based on Deep Learning DOI Open Access

Jean Paul Luyo Ballena,

Cristhian Pool Ortiz Pallihuanca,

Ernesto Adolfo Carrera-Salas

и другие.

International Journal of Advanced Computer Science and Applications, Год журнала: 2024, Номер 15(1)

Опубликована: Янв. 1, 2024

There are several techniques for predictive sales systems, in this study, a system based on different machine learning algorithms is developed trading company Lima. As any company, it needs to be accurate its calculations manage the volume of production or product purchases. With system, has mechanism order products from supplier predictions and estimates according projection sales. For Deep Learning technology neural network architectures GRU (Gated Recurrent Unit), LSTM (Long Short Term Memory) RNN (Recurrent Neural Network) were used, 10 sampled, quantities last 12 months obtained evaluation. The study found that architecture excels accuracy, significantly outperforming terms Mean Absolute Percentage Error (MAPE), achieving an average MAPE 7.07%, contrast 27.14% 36.17% RNN. These findings support effectiveness versatility time series prediction, demonstrating usefulness variety real-world applications.

Язык: Английский

Процитировано

0