Ítem
Acceso Abierto

Sistema de predicción de demanda utilizando técnicas de inteligencia artificial, enfocado en la línea de ritmo cardiaco en Medtronic Latinoamérica

Mostrar el registro sencillo de la publicación
dc.contributor.advisorCalvo López, John Pablo
dc.creatorCortés García, Julián David
dc.creatorGarcía Cuenca, María Claudia
dc.creator.degreeMagíster en Business Analytics
dc.creator.degreetypePart time
dc.date.accessioned2023-07-06T20:25:12Z
dc.date.available2023-07-06T20:25:12Z
dc.date.created2023-06-17
dc.date.embargoEndinfo:eu-repo/date/embargoEnd/2023-09-06
dc.descriptionActualmente la línea de ritmo cardiaco de Medtronic Latino-America, se ha visto notablemente impactada por el desabastecimiento de componentes clave y la falta de mano de obra, para la manufactura de dispositivos médicos como lo son marcapasos y desfibriladores médicos implantables. Para el año 2022 se ha visto una disminución de la disponibilidad del producto en aproximadamente en un 15%, lo que ha afectado notablemente a las ventas y las relaciones con cada uno de los clientes de la compañía. Teniendo en cuenta el problema planteado, el presente proyecto empresarial tiene como fin desarrollar un sistema de predicción de demanda, donde se evaluó el desempeño de dos técnicas de inteligencia artificial (Holt Winters y ARIMA), teniendo como base el comportamiento de la demanda en los últimos 4 años y aplicando la metodología CRISP-DM para su desarrollo. Al comparar las dos técnicas utilizadas, se logra identificar que la ARIMA presentó una mayor eficiencia con respecto a la técnica Holt Winters, por lo cual se recomienda aplicar la misma al momento de predecir la demanda de dispositivos.
dc.description.abstractCurrently, Medtronic Latin America's Cardiac Rhythm Product line has been significantly impacted by a shortage of key components and a lack of workforce for the manufacturing of medical devices such as pacemakers and implantable medical defibrillators. In 2022, there has been a decrease in product availability of approximately 15%, which has significantly affected sales and relationships with each of the company's customers. Considering the problem at hand, the aim of this business project is to develop a demand prediction system. The performance of two artificial intelligence techniques, Holt Winters and ARIMA, was evaluated based on the demand behavior over the past 4 years, using the CRISP-DM methodology for development. When comparing the two techniques used, it is identified that ARIMA demonstrated higher efficiency compared to the Holt Winters technique. Therefore, it is recommended to apply ARIMA when predicting device demand.
dc.description.sponsorshipMedtronic. Co
dc.format.extent46 pp
dc.format.mimetypeapplication/pdf
dc.identifier.doihttps://doi.org/10.48713/10336_40072
dc.identifier.urihttps://repository.urosario.edu.co/handle/10336/40072
dc.language.isospa
dc.publisherUniversidad del Rosario
dc.publisher.departmentEscuela de Administración
dc.publisher.departmentEscuela de Ingeniería, Ciencia y Tecnología
dc.publisher.programMaestría en Business Analytics
dc.rightsAttribution-NonCommercial-NoDerivatives 4.0 International*
dc.rights.accesRightsinfo:eu-repo/semantics/embargoedAccess
dc.rights.accesoRestringido (Temporalmente bloqueado)
dc.rights.urihttp://creativecommons.org/licenses/by-nc-nd/4.0/*
dc.source.bibliographicCitationAyala Castrejón, R. F., & Bucio Pacheco, C. (2020). Modelo ARIMA aplicado al tipo de cambio peso-dólar en el periodo 2016-2017 mediante ventanas temporales deslizantes. Mexican Journal of Economics & Finance / Revista Mexicana de Economia y Finanzas, 15(3), 331–354. http://ez.urosario.edu.co/login?url=https://search.ebscohost.com/login.aspx?direct=true&AuthType=ip&db=eoh&AN=EP144434364&lang=es&site=eds-live&scope=site
dc.source.bibliographicCitationBanerjee, P. (2020). ARIMA Model for Time Series Forecasting. Kaggle. https://www.kaggle.com/code/prashant111/arima-model-for-time-series-forecasting
dc.source.bibliographicCitationBrockwell, P. J., & Davis, R. A. (2016). Introduction to Time Series and Forecasting. Springer International Publishing. https://doi.org/10.1007/978-3-319-29854-2
dc.source.bibliographicCitationDe Livera, A. M., Hyndman, R. J., & Snyder, R. D. (2011). Forecasting Time Series With Complex Seasonal Patterns Using Exponential Smoothing. Journal of the American Statistical Association, 106(496), 1513–1527. https://doi.org/10.1198/jasa.2011.tm09771
dc.source.bibliographicCitationDyatkin, B., & Meng, Y. S. (2020). COVID-19 disrupts battery materials and manufacture supply chains, but outlook remains strong. MRS Bulletin, 45(9), 700–702. https://doi.org/10.1557/mrs.2020.239
dc.source.bibliographicCitationErsöz, N. Ş., Güner, P., Akbaş, A., & Baki̇R-Gungor, B. (2022). Comparative Performance Analysis of ARIMA, Prophet and Holt-Winters Forecasting Methods on European COVID-19 Data. International Journal of 3D Printing Technologies and Digital Industry. https://doi.org/10.46519/ij3dptdi.1120718
dc.source.bibliographicCitationGilley, S., Franks, L., Gayhardt, L., & Salgado, S. (2023). Azure Machine Learning architecture—Azure Architecture Center. Azure. https://learn.microsoft.com/en-us/azure/architecture/solution-ideas/articles/azure-machine-learning-solution-architecture
dc.source.bibliographicCitationHaffner, O., Kučera, E., & Moravčík, M. (2020). Sales Prediction of Svijany Slovakia, Ltd. Using Microsoft Azure Machine Learning and ARIMA. 2020 Cybernetics & Informatics (K&I), 1–9. https://doi.org/10.1109/KI48306.2020.9039875
dc.source.bibliographicCitationHyndman, R., & Athanasopoulos, G. (2018). Forecasting: Principles and Practice (2a ed.). https://otexts.com/fpp2/
dc.source.bibliographicCitationMakridakis, S., Wheelwright, S., & Hyndman, R. J. (1997). Forecasting: Methods and Applications. John Wiley & Sons. https://research.monash.edu/en/publications/forecasting-methods-and-applications-3rd-ed
dc.source.bibliographicCitationMedtronic. (2021). Misión. Nuestra Misión. https://latinoamerica.medtronic.com/xl-es/our-company/mission.html
dc.source.bibliographicCitationMedtronic. (2023). The Medtronic story: Leading healthcare technology innovation since 1949. https://www.medtronic.com/us-en/our-company/history.html
dc.source.bibliographicCitationMicrosoft Inc. (2023). Azure Machine Learning—ML as a Service | Microsoft Azure. https://azure.microsoft.com/en-us/products/machine-learning
dc.source.bibliographicCitationModgil, S., Gupta, S., Stekelorum, R., & Laguir, I. (2021). AI technologies and their impact on supply chain resilience during COVID-19. International Journal of Physical Distribution & Logistics Management, 52(2), 130–149. https://doi.org/10.1108/IJPDLM-12-2020-0434
dc.source.bibliographicCitationMontgomery, D. C., Jennings, C. L., & Kulahci, M. (2008). Introduction to time series analysis and forecasting. Wiley-Interscience.
dc.source.bibliographicCitationOracle. (2022, mayo 25). Cx_Oracle’s documentation. https://cx-oracle.readthedocs.io/en/latest/ Panwar, R., Pinkse, J., & De Marchi, V. (2022). The Future of Global Supply Chains in a Post-COVID-19 World. California Management Review, 64(2), 5–23. https://doi.org/10.1177/00081256211073355
dc.source.bibliographicCitationRodriguez, M., Cisneros, H., Arcos-Aviles, D., & Martinez, W. (2022). Forecast of photovoltaic generation in isolated rural areas of Ecuador using Holt-Winters and seasonal variation methods. IECON 2022 – 48th Annual Conference of the IEEE Industrial Electronics Society, Industrial Electronics Society, IECON 2022 – 48th Annual Conference of the IEEE, 1–6. https://doi.org/10.1109/IECON49645.2022.9968817
dc.source.bibliographicCitationTachu, E. (2022). A quantitative study of the relationship between cloud flexibility and on-premise flexibility. Issues In Information Systems, 23. https://doi.org/10.48009/1_iis_2022_117
dc.source.bibliographicCitationTimperley, J., Leeson, P., Mitchell, A. R., & Betts, T. (2019). Pacemakers and ICDs. Oxford University Press.
dc.source.bibliographicCitationTsao, C. W., Aday, A. W., Almarzooq, Z. I., Alonso, A., Beaton, A. Z., Bittencourt, M. S., Boehme, A. K., Buxton, A. E., Carson, A. P., Commodore-Mensah, Y., Elkind, M. S. V., Evenson, K. R., Eze-Nliam, C., Ferguson, J. F., Generoso, G., Ho, J. E., Kalani, R., Khan, S. S., Kissela, B. M., … Martin, S. S. (2022). Heart Disease and Stroke Statistics—2022 Update: A Report From the American Heart Association. Circulation, 145(8), e153–e639. https://doi.org/10.1161/CIR.0000000000001052
dc.source.bibliographicCitationWorld Health Oranization. (2021, junio 11). Cardiovascular diseases. https://www.who.int/news-room/fact-sheets/detail/cardiovascular-diseases-(cvds)
dc.source.instnameinstname:Universidad del Rosario
dc.source.reponamereponame:Repositorio Institucional EdocUR
dc.subjectRitmo cardiaco
dc.subjectModelo predictivo
dc.subjectInteligencia artificial
dc.subjectHolt Winters
dc.subjectARIMA
dc.subjectCRISP-DM
dc.subjectMedtronic
dc.subject.keywordCardiac Rhythm
dc.subject.keywordPredictive model
dc.subject.keywordForecast
dc.subject.keywordArtificial intelligence
dc.subject.keywordHolt Winters
dc.subject.keywordARIMA
dc.subject.keywordCRISP-DM
dc.subject.keywordMedtronic
dc.titleSistema de predicción de demanda utilizando técnicas de inteligencia artificial, enfocado en la línea de ritmo cardiaco en Medtronic Latinoamérica
dc.typebachelorThesis
dc.type.documentTrabajo de grado
dc.type.spaTrabajo de grado
local.department.reportEscuela de Administración
local.department.reportEscuela de Ciencias e Ingeniería
Archivos
Bloque original
Mostrando1 - 1 de 1
Miniatura
Nombre:
Sistema-de-prediccion-de-demanda-utilizando-CortesGarcia-JulianDavid-2023.pdf
Tamaño:
1.95 MB
Formato:
Adobe Portable Document Format
Descripción:
Descargar
Colecciones
Maestría en Business Analytics