Prediction of imported product demand in Peru using machine learning

Prediction of imported product demand in Peru using machine learning

dc.description.abstract	La gestión de la demanda de productos importados en Perú enfrenta desafíos significativos debido a la variabilidad del mercado, influida por factores económicos, políticos y climáticos. Este trabajo desarrolla un modelo predictivo basado en aprendizaje automático con el objetivo de mejorar la precisión en la estimación de la demanda, aplicando la metodología CRISP-DM y utilizando datos del Servicio Nacional de Sanidad Agraria (SENASA) correspondientes al periodo marzo de 2021 a diciembre de 2024. El modelo emplea técnicas de regresión lineal múltiple y considera variables como la ubicación aduanera, el tipo de importación, el tipo de producto y el país de origen. Se espera obtener un modelo robusto que apoye la planificación logística y la gestión de inventarios, fortaleciendo la toma de decisiones en el comercio internacional peruano.
dc.description.abstractenglish	Effectively managing the demand for imported products in Peru is a crucial challenge due to variability in market needs, influenced by economic, political and climatic factors. This study proposes the development of a predictive model based on machine learning to improve the accuracy of demand predictions, using the CRISP-DM methodology and a dataset from the National Agrarian Health Service (SENASA) covering March 2021 to December 2024. The model uses multiple linear regression techniques and analyzes variables such as customs location, import type, product type and country of origin, with the aim of reaching a confidence level above 50%. Expected results include a robust predictive model that optimizes logistics planning and inventory management, enabling companies to dynamically adapt to market fluctuations. This study contributes to improving supply chain efficiency and decision-making in the field of international trade in Peru.
dc.format.extent	36 páginas
dc.format.mimetype	application/pdf
dc.language.iso	en
dc.relation.references	Alam, T. (2019). Forecasting exports and imports through artificial neural network and autoregressive integrated moving average. Decision Science Letters, 8, 249–260. https://doi.org/10.5267/j.dsl.2019.2.001
dc.relation.references	Altman, N.S. (1992). An introduction to kernel and nearest-neighbor nonparametric regression. The American Statistician, 46(3), 175–185.
dc.relation.references	Anderson, C.M., Opaluch, J.J., & Grigalunas, T.A. (2009). The demand for import services at US container ports. Maritime Economics & Logistics, 11, 156–185. https://doi.org/10.1057/mel.2009.4
dc.relation.references	Breiman, L. (2001). Random forests. Machine Learning, 45(1), 5–32.
dc.relation.references	Chai, T., & Draxler, R.R. (2014). Root mean square error (RMSE) or mean absolute error (MAE)? – Arguments against avoiding RMSE in the literature. Geoscientific Model Development, 7(3), 1247–1250.
dc.relation.references	Chen, T., & Guestrin, C. (2016). XGBoost: A scalable tree boosting system. Proceedings of the 22nd ACM SIGKDD Conference, 785–794.
dc.relation.references	Chou, C.C., Chu, C.W., & Liang, G.S. (2008). A modified regression model for forecasting the volumes of Taiwan’s import containers. Mathematical and Computer Modelling, 47, 797–807.
dc.relation.references	Costantiello, A., Laureti, L., & Leogrande, A. (2010). Estimation and machine learning prediction of imports of goods in European countries. AJHSSR.
dc.relation.references	Drucker, H. (1997). Improving regressors using boosting techniques. ICML, 107–115.
dc.relation.references	Efron, B., Hastie, T., Johnstone, I., & Tibshirani, R. (2004). Least angle regression. Annals of Statistics, 32(2), 407–499.
dc.relation.references	Fashoto, S.G., Mbunge, E., Ogunleye, G., & Burg, J.V.D. (2021). Implementation of machine learning for predicting maize crop yields. Malaysian Journal of Computing, 6, 679–697.
dc.relation.references	Fernández, A., del Rio, S., & Herrera, F. (2018). Learning with logarithmic loss and evaluation measures in regression problems. IJCNN.
dc.relation.references	Friedman, J.H. (2001). Greedy function approximation: A gradient boosting machine. Annals of Statistics, 1189–1232.
dc.relation.references	Geurts, P., Ernst, D., & Wehenkel, L. (2006). Extremely randomized trees. Machine Learning, 63(1), 3–42.
dc.relation.references	Gosasang, V., Chandraprakaikul, W., & Kiattisin, S. (2011). Comparison of forecasting techniques for container throughput at Bangkok port. Asian Journal of Shipping and Logistics, 27, 463–482.
dc.relation.references	Hoerl, A.E., & Kennard, R.W. (1970). Ridge regression: Biased estimation for nonorthogonal problems. Technometrics, 12(1), 55–67.
dc.relation.references	Horák, J., & Machová, V. (2019). Comparison of neural networks and regression time series forecasting of US imports from PRC. Institute of Technology and Business.
dc.relation.references	Juan, B.C.C.S. (2015). Régimen de importación de bienes: Llegada y desaduanamiento de mercancías. Banco de la República.
dc.relation.references	Kim, S., & Kim, H. (2016). A new metric of absolute percentage error for intermittent demand forecasts. International Journal of Forecasting, 32(3), 669–679.
dc.relation.references	Milad, M.A., Ibrahim, R.I., & Marappan, S. (2015). Regression model building and forecasting on imports in Malaysia. Australian Journal of Basic and Applied Sciences.
dc.relation.references	Nagelkerke, N.J.D. (1991). A note on a general definition of the coefficient of determination. Biometrika, 78(3), 691–692.
dc.relation.references	Banco Central de Reserva del Perú (2021). Reporte de inflación – septiembre 2021.
dc.relation.references	Ministerio de Desarrollo Agrario y Riego del Perú (2024). Importación de productos vegetales en SENASA 2021–2024. datosabiertos.gob.pe
dc.relation.references	PyCaret. (2024). PyCaret documentation. https://pycaret.gitbook.io/docs
dc.relation.references	Quinlan, J.R. (1986). Induction of Decision Trees. Machine Learning, 1, 81–106.
dc.relation.references	Razia, S.A., & Pranav, R. (2022). Predicting the import and export of commodities using SVR and LSTM models. International Journal of Computing and Digital Systems, 11, 635+.
dc.relation.references	Shao, Y.E., Lu, C.J., & Hou, C.D. (2014). Hybrid soft computing schemes for the prediction of import demand of crude oil in Taiwan. Mathematical Problems in Engineering.
dc.relation.references	Son, Y., & Kim, H. (2012). Forecasting Export Import Container Cargoes using Decision Tree Analysis. 28, 193–207.
dc.relation.references	Tibshirani, R. (1996). Regression shrinkage and selection via the LASSO. JRSS-B, 58(1), 267–288.
dc.relation.references	Willmott, C.J., & Matsuura, K. (2005). Advantages of MAE over RMSE in model performance assessment. Climate Research, 30(1), 79–82.
dc.relation.references	Yang, C.H., Lee, C.F., & Chang, P.Y. (2023). Predicting global trade using deep learning models. Expert Systems with Applications, 218, 119590.
dc.relation.references	Zou, H., & Hastie, T. (2005). Regularization and variable selection via the elastic net. JRSS-B, 67(2), 301–320.
dc.relation.references	Zúñiga, J.J.E. (2020). Aplicación de metodología CRISP-DM para segmentación geográfica de una base de datos pública. Ingeniería Investigación y Tecnología, 21(1), 1–13.
dc.subject	Aprendizaje automático
dc.subject	Predicción de demanda
dc.subject	Importaciones
dc.subject	Metodología CRISP-DM
dc.subject	Modelos de regresión
dc.subject	Logística y Perú.
dc.subject.keyword	Machine learning
dc.subject.keyword	Demand prediction
dc.subject.keyword	Imports
dc.subject.keyword	CRISP-DM methodology
dc.subject.keyword	Regression models
dc.subject.keyword	Predictive modeling
dc.subject.keyword	Peru
dc.subject.keyword	Supply chain management and supply chain optimization.
dc.subject.lemb	Comercio internacional - Importaciones
dc.subject.lemb	Demanda de productos - Modelos matemáticos
dc.subject.lemb	Logística - Gestión de inventarios
dc.title	Prediction of imported product demand in Peru using machine learning
dc.type.coar	http://purl.org/coar/resource_type/c_bdcc

Archivos

Bloque original

Mostrando 1 - 1 de 1

Nombre:: PREDICTION_OF_IMPORTED_PRODUCT_DEMAND_IN_PERU_USING_MACHINE_LEARNING.pdf
Tamaño:: 802.59 KB
Formato:: Adobe Portable Document Format
Descripción:: Tesis

Descargar

Bloque de licencias

Mostrando 1 - 2 de 2

Nombre:: license.txt
Tamaño:: 3.28 KB
Formato:: Item-specific license agreed upon to submission
Descripción:

Descargar

Nombre:: FOR-EFE-GDB-007_AUTORIZACION_DE_PUBLICACION_DE_TESIS_O_TRABAJO_DE_GRADO (1).pdf
Tamaño:: 222.98 KB
Formato:: Adobe Portable Document Format
Descripción:: Carta de autorización

Descargar

Colecciones

Maestría en Ingeniería y Analítica de Datos