Supervised Learning Algorithms for Sales Projection of Ecuadorian Shrimp with Python Programming Language
This research develops the best approximation for the non-linear projection of sales of a shrimp company listed on the Stock Exchange, in contrast to published corporate linear estimates. It starts from the search for data through a SWOT of the variable of interest: average price of Ecuadorian shrim...
| Autor: | |
|---|---|
| Formato: | artículo |
| Estado: | Versión publicada |
| Fecha de publicación: | 2022 |
| País: | Ecuador |
| Recursos: | Universidad Tecnológica Equinoccial |
| Repositorio: | Revistas Universidad Tecnológica Equinoccial |
| Idioma: | español |
| OAI Identifier: | oai:ojs.ute.edu.ec:article/996 |
| Acesso em linha: | https://revistas.ute.edu.ec/index.php/economia-y-negocios/article/view/996 |
| Access Level: | acceso abierto |
| Palavra-chave: | Python programming language Econometrics Supervised learning Sales projection Shrimp industry Econometría Aprendizaje supervisado Lenguaje de programación python Proyección de ventas Industria camaronera |
| id |
EC_2c446409415bb7ca3c6d6fa7d90c6cc9 |
|---|---|
| oai_identifier_str |
oai:ojs.ute.edu.ec:article/996 |
| network_acronym_str |
EC |
| network_name_str |
Ecuador |
| repository_id_str |
|
| dc.title.none.fl_str_mv |
Supervised Learning Algorithms for Sales Projection of Ecuadorian Shrimp with Python Programming Language Algoritmos de Aprendizaje Supervisado para Proyección de Ventas de Camarón Ecuatoriano con Lenguaje de Programación Python |
| title |
Supervised Learning Algorithms for Sales Projection of Ecuadorian Shrimp with Python Programming Language |
| spellingShingle |
Supervised Learning Algorithms for Sales Projection of Ecuadorian Shrimp with Python Programming Language Cordero-Torres, Bernardo Patricio Python programming language Econometrics Supervised learning Sales projection Shrimp industry Econometría Aprendizaje supervisado Lenguaje de programación python Proyección de ventas Industria camaronera |
| title_short |
Supervised Learning Algorithms for Sales Projection of Ecuadorian Shrimp with Python Programming Language |
| title_full |
Supervised Learning Algorithms for Sales Projection of Ecuadorian Shrimp with Python Programming Language |
| title_fullStr |
Supervised Learning Algorithms for Sales Projection of Ecuadorian Shrimp with Python Programming Language |
| title_full_unstemmed |
Supervised Learning Algorithms for Sales Projection of Ecuadorian Shrimp with Python Programming Language |
| title_sort |
Supervised Learning Algorithms for Sales Projection of Ecuadorian Shrimp with Python Programming Language |
| dc.creator.none.fl_str_mv |
Cordero-Torres, Bernardo Patricio |
| author |
Cordero-Torres, Bernardo Patricio |
| author_facet |
Cordero-Torres, Bernardo Patricio |
| author_role |
author |
| dc.subject.none.fl_str_mv |
Python programming language Econometrics Supervised learning Sales projection Shrimp industry Econometría Aprendizaje supervisado Lenguaje de programación python Proyección de ventas Industria camaronera |
| topic |
Python programming language Econometrics Supervised learning Sales projection Shrimp industry Econometría Aprendizaje supervisado Lenguaje de programación python Proyección de ventas Industria camaronera |
| description |
This research develops the best approximation for the non-linear projection of sales of a shrimp company listed on the Stock Exchange, in contrast to published corporate linear estimates. It starts from the search for data through a SWOT of the variable of interest: average price of Ecuadorian shrimp, identifying the variables: explanatory of shrimp prices in the United States, the observed change of the dollar against the yuan, Ecuadorian exports, US imports of Indian shrimp, barrel of WTI crude oil and the FPI™ salmon price index, as the most influential interpreted by the result of an adjusted coefficient of determination of 0.807. The instrumentation of the econometric model evaluates the statistical indicators of three predictive supervised learning linear regression algorithms in the Python programming language, with Ridge being the model with the lowest mean square error equal to 0.274. Based on five-year assumptions with Ridge, sales are forecast from 2021 to 2025, correlating the variables historical revenue of the shrimp company versus the average price of shrimp through polynomial interpolation, comparing both resulting trend lines showing that the expected revenues maintain a behavior non-linear according to its historical performance. |
| publishDate |
2022 |
| dc.date.none.fl_str_mv |
2022-12-01 |
| dc.type.none.fl_str_mv |
info:eu-repo/semantics/article info:eu-repo/semantics/publishedVersion Peer-reviewed Evaluado por pares |
| format |
article |
| status_str |
publishedVersion |
| dc.identifier.none.fl_str_mv |
https://revistas.ute.edu.ec/index.php/economia-y-negocios/article/view/996 10.29019/eyn.v13i2.996 |
| url |
https://revistas.ute.edu.ec/index.php/economia-y-negocios/article/view/996 |
| identifier_str_mv |
10.29019/eyn.v13i2.996 |
| dc.language.none.fl_str_mv |
spa |
| language |
spa |
| dc.relation.none.fl_str_mv |
https://revistas.ute.edu.ec/index.php/economia-y-negocios/article/view/996/882 https://revistas.ute.edu.ec/index.php/economia-y-negocios/article/view/996/883 |
| dc.rights.none.fl_str_mv |
Derechos de autor 2022 El Autor https://creativecommons.org/licenses/by/4.0/ info:eu-repo/semantics/openAccess |
| rights_invalid_str_mv |
Derechos de autor 2022 El Autor https://creativecommons.org/licenses/by/4.0/ |
| eu_rights_str_mv |
openAccess |
| dc.format.none.fl_str_mv |
application/pdf text/html |
| dc.publisher.none.fl_str_mv |
Universidad UTE |
| publisher.none.fl_str_mv |
Universidad UTE |
| dc.source.none.fl_str_mv |
Economía y Negocios; Vol. 13 No. 2 (2022): Journal Economía y Negocios (July - December 2022); 30-51 Economía y Negocios; Vol. 13 Núm. 2 (2022): Revista Economía y Negocios (Julio - Diciembre 2022); 30-51 2602-8050 10.29019/eyn.v13i2 reponame:Revistas Universidad Tecnológica Equinoccial instname:Universidad Tecnológica Equinoccial instacron:UTE |
| instname_str |
Universidad Tecnológica Equinoccial |
| instacron_str |
UTE |
| institution |
UTE |
| reponame_str |
Revistas Universidad Tecnológica Equinoccial |
| collection |
Revistas Universidad Tecnológica Equinoccial |
| repository.name.fl_str_mv |
Revistas Universidad Tecnológica Equinoccial - Universidad Tecnológica Equinoccial |
| repository.mail.fl_str_mv |
. |
| _version_ |
1868999379711426560 |
| spelling |
Supervised Learning Algorithms for Sales Projection of Ecuadorian Shrimp with Python Programming LanguageAlgoritmos de Aprendizaje Supervisado para Proyección de Ventas de Camarón Ecuatoriano con Lenguaje de Programación PythonCordero-Torres, Bernardo PatricioPython programming languageEconometricsSupervised learningSales projectionShrimp industryEconometríaAprendizaje supervisadoLenguaje de programación pythonProyección de ventasIndustria camaroneraThis research develops the best approximation for the non-linear projection of sales of a shrimp company listed on the Stock Exchange, in contrast to published corporate linear estimates. It starts from the search for data through a SWOT of the variable of interest: average price of Ecuadorian shrimp, identifying the variables: explanatory of shrimp prices in the United States, the observed change of the dollar against the yuan, Ecuadorian exports, US imports of Indian shrimp, barrel of WTI crude oil and the FPI™ salmon price index, as the most influential interpreted by the result of an adjusted coefficient of determination of 0.807. The instrumentation of the econometric model evaluates the statistical indicators of three predictive supervised learning linear regression algorithms in the Python programming language, with Ridge being the model with the lowest mean square error equal to 0.274. Based on five-year assumptions with Ridge, sales are forecast from 2021 to 2025, correlating the variables historical revenue of the shrimp company versus the average price of shrimp through polynomial interpolation, comparing both resulting trend lines showing that the expected revenues maintain a behavior non-linear according to its historical performance.Esta investigación desarrolla la mejor aproximación para la proyección no lineal de las ventas de una empresa camaronera que cotiza en la bolsa de valores, en contraste con las estimaciones lineales corporativas publicadas. Se parte de la búsqueda de datos a través de un FODA de la variable de interés: precio promedio del camarón ecuatoriano, identificando las variables explicativas de precios del camarón en Estados Unidos, el cambio observado del dólar frente al yuan, exportaciones ecuatorianas, importaciones estadounidenses de camarón indio, barril de crudo WTI y el índice de precios FPI™ del salmón, esto como las variables más influyentes interpretadas por el resultado de un coeficiente de determinación ajustado de 0.807. La instrumentación del modelo econométrico evalúa los indicadores estadísticos de tres algoritmos de regresión lineal de aprendizaje supervisado predictivo en el lenguaje de programación Python, siendo Ridge el modelo con menor error cuadrático medio igual a 0.274. Basándose en supuestos a cinco años con Ridge se pronostican ventas desde 2021 a 2025, correlacionando las variables ingresos históricos de la empresa camaronera versus el precio promedio del camarón mediante interpolación polinomial. Comparando ambas líneas de tendencia resultantes se demuestra que los ingresos esperados conservan un comportamiento no lineal acorde con su desempeño histórico.Universidad UTE2022-12-01info:eu-repo/semantics/articleinfo:eu-repo/semantics/publishedVersionPeer-reviewedEvaluado por paresapplication/pdftext/htmlhttps://revistas.ute.edu.ec/index.php/economia-y-negocios/article/view/99610.29019/eyn.v13i2.996Economía y Negocios; Vol. 13 No. 2 (2022): Journal Economía y Negocios (July - December 2022); 30-51Economía y Negocios; Vol. 13 Núm. 2 (2022): Revista Economía y Negocios (Julio - Diciembre 2022); 30-512602-805010.29019/eyn.v13i2reponame:Revistas Universidad Tecnológica Equinoccialinstname:Universidad Tecnológica Equinoccialinstacron:UTEspahttps://revistas.ute.edu.ec/index.php/economia-y-negocios/article/view/996/882https://revistas.ute.edu.ec/index.php/economia-y-negocios/article/view/996/883Derechos de autor 2022 El Autorhttps://creativecommons.org/licenses/by/4.0/info:eu-repo/semantics/openAccess2023-09-19T20:14:05Zoai:ojs.ute.edu.ec:article/996Institucionalhttps://www.ute.edu.ec/revistas-ute/Universidad privadahttps://www.ute.edu.ec/..Ecuador.1390-65421390-6542opendoar:02023-09-19T20:14:05Revistas Universidad Tecnológica Equinoccial - Universidad Tecnológica Equinoccialfalse |
| score |
14.965132 |