Mostrar el registro sencillo del ítem

Desarrollo de un prototipo de sistema de facturación e inventarios para tiendas minoristas de ropa que mediante redes neuronales mejore el control de inventarios

dc.contributor.advisorMoreno Corzo, Feisar Enriquespa
dc.contributor.advisorTalero Sarmiento, Leonardo Hernánspa
dc.contributor.authorBernal Dávila, Nicolás Andrésspa
dc.contributor.authorLópez Abril, Álvaro Steveenspa
dc.coverage.spatialColombiaspa
dc.date.accessioned2021-01-26T15:11:07Z
dc.date.available2021-01-26T15:11:07Z
dc.date.issued2020
dc.identifier.urihttp://hdl.handle.net/20.500.12749/12050
dc.description.abstractEl manejo de inventarios es una de las actividades mas complejas e importantes de las empresas, esto es así debido a la alta incertidumbre de varios factores que afectan esta actividad. Entre esos factores se destaca la demanda de los productos en el mercado. Un mal manejo de inventarios puede llevar a perdidas considerables por la manutención del mismo o por costos asociados a faltantes. Para solucionar esto el presente proyecto propone el desarrollo de un software de facturación POS con una red neuronal artificial implementada para calcular la demanda de los productos, disminuyendo así la incertidumbre que esto genera y por consiguiente reducir el riesgo de tomar decisiones desacertadasen la gestión de inventarios. Además, se implementará un modelo matemático EOQ que utilizará la demanda predicha para calcular la cantidad optima de productos a pedir enfocado a minimizar los costos generados por el pedido y la manutención de productos. Para la generación de la red neuronal se probarán 2 métodos de normalización diferentes en 5 arquitecturas de redes neuronales utilizando varios conjuntos de datos con el fin de determinar que tan precisas pueden ser estas en este caso y también cual es la mejor que se adapta a este problema. De esto se obtuvo que tanto las arquitecturas con mayor cantidad de neuronas como las arquitecturas con neuronas decrecientes tienen un mejor rendimiento al momento de la predicción de la demanda.spa
dc.description.tableofcontentsINTRODUCCIÓN 10 1. PLANTEAMIENTO DEL PROBLEMA Y JUSTIFICACION 11 2. OBJETIVOS 12 2.1 OBJETIVO GENERAL 12 2.2 OBJETIVOS ESPECIFICOS 12 3. RESULTADOS ESPERADOS 13 4. MARCO TEORICO 15 4.1 POINT OF SALE (POS) 15 4.2 INVENTARIOS 18 4.3 INTELIGENCIA ARTIFICIAL (IA) 19 5. ESTADO DEL ARTE 28 5.1 MACHINE LEARNING METHODS FOR DEMAND ESTIMATION 28 5.2 PREDICTING STOCK AND STOCK PRICE INDEX MOVEMENT USING TREND DETERMINISTIC DATA PREPARATION AND MACHINE LEARNING TECHNIQUES 28 5.3 A COMPARATIVE STUDY OF SUPERVISED MACHINE LEARNING ALGORITHMS FOR STOCK MARKET TREND PREDICTION 29 5.4 STOCK MARKET PREDICTION USING AN IMPROVED TRAINING ALGORITHM OF NEURAL NETWORK 29 5.5 OPTIMAL INVENTORY MODEL UNDER STOCK AND TIME DEPENDENT DEMAND FOR TIME VARYING DETERIORATION RATE WITH SHORTAGES 29 5.6 INVENTORY AND PRICING MODEL WITH PRICE-DEPENDENT DEMAND, TIME-VARYING HOLDING COST AND QUANTITY DISCOUNTS 30 5.7 JPOS 30 5.8 APLICACIÓN DE UN MODELO DE INVENTARIOS MULTIPRODUCTO PARA LAS PYMES EN BOGOTA 31 5.9 SOLUTION OF A PROBABILISTIC INVENTORY MODEL WITH CHANCE CONSTRAINTS: A GENERAL FUZZY PROGRAMMING AND INTUITIONISTIC FUZZY OPTIMIZATION APPROACH 31 6. METODOLOGÍA 32 6.1 METODOLOGÍA PROPUESTA 32 6.1 METODOLOGÍA IMPLEMENTADA 33 7. RESULTADOS 66 7.1 PRODUCTO FINAL 66 7.2 RED NEURONAL 66 7.3 PRUEBAS REALIZADAS 67 7.4 RESULTADOS OBTENIDOS 69 7.5 ANALISIS DE RESULTADOS 71 8. CONCLUSIONES Y RECOMENDACIONES 72 8.1 CONCLUSIONES 72 8.2 RECOMENDACIONES 72 9. BIBLIOGRAFIA 74 ANEXOS 76spa
dc.format.mimetypeapplication/pdfspa
dc.language.isospaspa
dc.rights.urihttp://creativecommons.org/licenses/by-nc-nd/2.5/co/*
dc.titleDesarrollo de un prototipo de sistema de facturación e inventarios para tiendas minoristas de ropa que mediante redes neuronales mejore el control de inventariosspa
dc.title.translatedDevelopment of a billing and inventory system prototype for clothing retail stores that improves inventory control through neural networksspa
dc.degree.nameIngeniero de Sistemasspa
dc.publisher.grantorUniversidad Autónoma de Bucaramanga UNABspa
dc.rights.localAbierto (Texto Completo)spa
dc.publisher.facultyFacultad Ingenieríaspa
dc.publisher.programPregrado Ingeniería de Sistemasspa
dc.description.degreelevelPregradospa
dc.type.driverinfo:eu-repo/semantics/bachelorThesis
dc.type.localTrabajo de Gradospa
dc.type.coarhttp://purl.org/coar/resource_type/c_7a1f
dc.subject.keywordsSystems engineereng
dc.subject.keywordsTechnological innovationseng
dc.subject.keywordsPOS systemeng
dc.subject.keywordsStock managementeng
dc.subject.keywordsNeural networkeng
dc.subject.keywordsArtificial intelligenceeng
dc.subject.keywordsEOQeng
dc.subject.keywordsInventory controleng
dc.subject.keywordsProduction controleng
dc.subject.keywordsRetail commerceeng
dc.subject.keywordsCommerceeng
dc.identifier.instnameinstname:Universidad Autónoma de Bucaramanga - UNABspa
dc.identifier.reponamereponame:Repositorio Institucional UNABspa
dc.type.hasversioninfo:eu-repo/semantics/acceptedVersion
dc.rights.accessrightsinfo:eu-repo/semantics/openAccessspa
dc.rights.accessrightshttp://purl.org/coar/access_right/c_abf2spa
dc.relation.referencesAlfares, H. K., & Ghaithan, A. M. (2016). Inventory and pricing model with pricedependent demand, time-varying holding cost, and quantity discounts.spa
dc.relation.referencesAparra. (2016). Applying genetic algorithms to define a trading system. https://quantdare.com/ga-to-define-a-trading-systemspa
dc.relation.referencesBajari, P., Nekipelov, D., Ryan, S. P., & Yang, M. (2015). Machine Learning Methods for Demand Estimationspa
dc.relation.referencesBanerhee, R., & Banerjee, S. (2012). Solution of a Probabilistic Inventory Model with Chance Constraints: A General Fuzzy Programming and Intuitionistic Fuzzy Optimization Approach. 19spa
dc.relation.referencesBarber, D. (2012). Bayesian Reasoning and Machine Learning. In Bayesian Reasoning and Machine Learningspa
dc.relation.referencesBillan, M., Waheed, S., & Hanifa, A. (2016). Stock market prediction using an improved training algorithm of neural networkspa
dc.relation.referencesEditorial Vertice. (2009). Gestion del Punto de Venta (Editorial Vertice (ed.); 1st ed.). Editorial Vertice.spa
dc.relation.referencesEmblem, A., & Emblem, H. (1990). Packaging Technology - Fundamentals, Materials and Processes. In A. Emblem & H. Emblem (Eds.), Social Work with Groups (1st ed.). Woodhead Publishing Limitedspa
dc.relation.referencesFarahani, R. Z., Rezapour, S., & Kardar, L. (2011). Logistics Operations and Management - Concepts and Models (1st ed.). Elsevier.spa
dc.relation.referencesFellows, P. J. (2017). Food Processing Technology - Principles and Practice (4th Edition) (P. J. Fellows (ed.); 4th ed.). Elsevier.spa
dc.relation.referencesGurney, K. (1997). An introduction to neural networks. UCL Press.spa
dc.relation.referencesHaykin, S. (2009). Neural Networks and Learning Machines (Vol. 3). Pearson. https://doi.org/978-0131471399spa
dc.relation.referencesHurwitz, J., & Kirsch, D. (2018). Machine Learning Machine Learning For Dummies. In John Wiley & Sons, Inc. Rev Menglespa
dc.relation.referencesJoshi, P. (2017). Artificial Intelligence with Python. In Artificial Intelligence with Uncertainty. Packt Publishing Ltd. https://doi.org/10.1201/9781315366951spa
dc.relation.referencesJPOS. (n.d.). JPOS. http://www.jpos.org/aboutspa
dc.relation.referencesKiggins, J. (2018). Avocado Pricesspa
dc.relation.referencesKumar, I., Dogra, K., Utreja, C., & Yadav, P. (2018). A Comparative Study of Supervised Machine Learning Algorithms for Stock Market Trend Prediction. https://ieeexplore-ieeeorg. aure.unab.edu.co/document/8473214spa
dc.relation.referencesL. Kit, Y. (2009). Wiley Encyclopedia of Packaging Technology (Y. L. Kit (ed.); 3rd ed.). John Wiley & Sons.spa
dc.relation.referencesLaza, C. A. (2019). Operaciones de caja en la venta. UF0035 (Editorial Tutor 75 Formación (ed.); 1st ed.). Editorial Tutor Formación.spa
dc.relation.referencesMitchell, M. (1999). An Introduction to Genetic Algorithms. In Artificial Life. https://doi.org/10.1162/artl.1997.3.63spa
dc.relation.referencesMwansele, H., Sichona, F., & Akarro, R. (2011). Determination of Inventory Control Policies at Urafiki Textile Mills Co Ltd in Dar-es-Salaam, Tanzaniaspa
dc.relation.referencesPatel, J., Shah, S., & Thakkar, P. (2015). Predicting stock and stock price index movement using Trend Deterministic Data Preparation and machine learning techniquesspa
dc.relation.referencesPereira Soler, F., & Carci Grandes, J. (2016). Dirección y contabilidad financiera.pdf (F. Pereira Soler & J. Carci Grandes (eds.); 1st ed.). Ediciones Universidad de Navarra.spa
dc.relation.referencesPrasad, K., & Mukherjee, B. (2014). Optimal inventory model under stock and time dependent demand for time varying deterioration rate with shortagesspa
dc.relation.referencesRamirez, L., Soto, D., Perez, M., & Gamez, W. (2009). Aplicacion de un modelo de inventarios multiproducto para las PYMES en Bogotá. 8.spa
dc.relation.referencesRoss, T. J. (2010). Fuzzy Logic with Engineering Applications: Third Edition. In Fuzzy Logic with Engineering Applications: Third Edition. https://doi.org/10.1002/9781119994374spa
dc.relation.referencesRufe, P. D. (2013). Fundamentals of Manufacturing (3rd Edition) (P. D. Rufe (ed.); 3rd ed.). Society of Manufacturing Engineers.spa
dc.relation.referencesRussel, S. N. P. (2010). Artificial Inteligence: A Modern Approach (3rd ed).spa
dc.relation.referencesSandom, C., & Harvey, R. S. (2011). Human Factors for Engineers (C. Sandom & R. Harvey (eds.); 1st ed.). The Institution of Engineering and Technologyspa
dc.relation.referencesSivanandam, S. ., & Deepa, S. . (2008). Introduction to Genetic Algorithms.spa
dc.relation.referencesSuchok, S. (2015). Mathematica Data Analysis - Learn and Explore the Fundamentals of Data Analysis with the Power of Mathematica (S. Suchok (ed.); 1st ed.). 5 Packt Publishingspa
dc.relation.referencesTolpygo, A. (2016). Nuts and Bolts of Portfolio Prediction: Reinforcement Learning. https://sflscientific.com/data-science-blog/2016/12/16/portfoliopredictionspa
dc.relation.referencesZapata Cortes, J. A. (2014). Fundamentos de la gestión de inventarios (J. A. Zapata Cortes (ed.); 1st ed.). Centro Editorial Esumerspa
dc.contributor.cvlachttps://scienti.minciencias.gov.co/cvlac/visualizador/generarCurriculoCv.do?cod_rh=0001499008*
dc.contributor.orcidhttps://orcid.org/0000-0002-5007-3422*
dc.subject.lembIngeniería de sistemasspa
dc.subject.lembInnovaciones tecnológicasspa
dc.subject.lembControl de inventariosspa
dc.subject.lembControl de la producciónspa
dc.subject.lembComercio minoristaspa
dc.subject.lembComerciospa
dc.identifier.repourlrepourl:https://repository.unab.edu.cospa
dc.description.abstractenglishFor companies, stock management is one of the most important and complex activities, that’s because there are many uncertain variables which have a deep impact in these activities. Between these variables the one which more highlights is product demand. A wrong stock management could cause important economic losses because of stock maintenance or cost associated to shortages. In order to solve that, this project aims to develop a POS system with an artificial neural network which calculates products demand, thus reducing the uncertainty generated by this variable and therefore it will decrease the risk of making poor inventory management decisions. Also, an EOQ model will be implemented for take the predicted demand and calculate the optimal stock focused on minimizing costs produced by inventories. To get the best neural network architecture 2 normalization methods will be tested in 5 neural network architectures using some different datasets in order to get how much accurate are these and also which of these architectures gets the best results. Results show that both architectures with the most neurons and architectures with decreasing neurons have the best performance by predicting product demand.eng
dc.subject.proposalSoftware POSspa
dc.subject.proposalManejo de inventariosspa
dc.subject.proposalRed neuronalspa
dc.subject.proposalInteligencia artificialspa
dc.subject.proposalEOQspa
dc.type.redcolhttp://purl.org/redcol/resource_type/TP
dc.rights.creativecommonsAtribución-NoComercial-SinDerivadas 2.5 Colombia*
dc.coverage.campusUNAB Campus Bucaramangaspa
dc.description.learningmodalityModalidad Presencialspa


Ficheros en el ítem

Thumbnail
Nombre:
2020_Tesis_Nicolas_Andres_Bern ...
Tamaño:
4.302Mb
Formato:
PDF
Descripción:
Tesis
Ver/
Thumbnail
Nombre:
2020_Licencia_Nicolas_Andres_B ...
Tamaño:
102.3Kb
Formato:
PDF
Descripción:
Licencia
Ver/

Este ítem aparece en la(s) siguiente(s) colección(ones)

Mostrar el registro sencillo del ítem

Atribución-NoComercial-SinDerivadas 2.5 Colombia
Excepto si se señala otra cosa, la licencia del ítem se describe como Atribución-NoComercial-SinDerivadas 2.5 Colombia