Powered by OpenAIRE graph
Found an issue? Give us feedback
image/svg+xml art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos Open Access logo, converted into svg, designed by PLoS. This version with transparent background. http://commons.wikimedia.org/wiki/File:Open_Access_logo_PLoS_white.svg art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos http://www.plos.org/ Recolector de Cienci...arrow_drop_down
image/svg+xml art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos Open Access logo, converted into svg, designed by PLoS. This version with transparent background. http://commons.wikimedia.org/wiki/File:Open_Access_logo_PLoS_white.svg art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos http://www.plos.org/
addClaim

This Research product is the result of merged Research products in OpenAIRE.

You have already added 0 works in your ORCID record related to the merged Research product.

Previsión de demanda mediante técnicas de machine learning

Authors: Calvo Martucci, Sebastián;

Previsión de demanda mediante técnicas de machine learning

Abstract

La gestión del inventario es crucial para el rendimiento operativo de una empresa, enfrentando desafíos que van desde problemas con proveedores hasta cambios inesperados en la demanda y promociones del mercado. Este proyecto aborda esta complejidad mediante la creación de un modelo predictivo para estimar con mayor precisión la demanda y facilitar la gestión del stock. Para lograr esta meta, se comienza con la justificación y contextualización del proyecto, estableciendo los objetivos y la metodología de trabajo. Posteriormente se revisa la bibliografía existente en cuanto a soluciones propuestas para tener un punto de partida. Además, se investiga sobre una técnica de estimación del cálculo de inventario. Luego, se analizan los datos de una empresa de venta de productos de automoción, llevando a cabo la exploración y limpieza de los datos para garantizar su calidad. Se buscan correlaciones entre variables, se crean features y se aplican técnicas de clustering. Una vez completada la etapa de exploración y preprocesamiento, se procede con la selección de modelos, explicando los indicadores de precisión e hiperparámetros utilizados. Posteriormente se evalúan y clasifican los resultados de precisión obtenidos de los diferentes modelos seleccionados. Finalmente, se estudia el impacto económico de la mejora del algoritmo y se presentan las conclusiones del proyecto, junto con las lecciones aprendidas, el logro de los objetivos y las posibles líneas de trabajo futuro.

Stock management is crucial for a company’s operational performance, facing challenges ranging from supplier issues to unexpected changes in demand and market promotions. This project tackles this complexity by creating a predictive model to estimate demand more accurately and facilitate stock management. To achieve this goal, the project begins with the justification and contextualization, establishing objectives and the working methodology. Then, existing literature on proposed solutions is reviewed to provide a foundation. Additionally, a technique for estimating inventory calculations is investigated. Following this, data from a company that sells automotive products is analyzed, involving data exploration and cleaning to ensure quality. Correlations between variables are examined, features are created, and clustering techniques are applied. Once the exploration and preprocessing stages are completed, model selection proceeds, detailing the accuracy indicators and hyperparameters used. Subsequently, the accuracy results from the different selected models are evaluated and ranked. Finally, the economic impact of the improved algorithm is studied, and the project’s conclusions are presented, including lessons learned, achievement of objectives, and potential future work directions.

Keywords

predictive model, machine learning, Aprenentatge automàtic -- TFM, aprendizaje automático, modelo predictivo, gestión de demanda, predictive algorithms, stock management, Machine learning -- TFM, algoritmo predictivo

  • BIP!
    Impact byBIP!
    selected citations
    These citations are derived from selected sources.
    This is an alternative to the "Influence" indicator, which also reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).
    0
    popularity
    This indicator reflects the "current" impact/attention (the "hype") of an article in the research community at large, based on the underlying citation network.
    Average
    influence
    This indicator reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).
    Average
    impulse
    This indicator reflects the initial momentum of an article directly after its publication, based on the underlying citation network.
    Average
Powered by OpenAIRE graph
Found an issue? Give us feedback
selected citations
These citations are derived from selected sources.
This is an alternative to the "Influence" indicator, which also reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).
BIP!Citations provided by BIP!
popularity
This indicator reflects the "current" impact/attention (the "hype") of an article in the research community at large, based on the underlying citation network.
BIP!Popularity provided by BIP!
influence
This indicator reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).
BIP!Influence provided by BIP!
impulse
This indicator reflects the initial momentum of an article directly after its publication, based on the underlying citation network.
BIP!Impulse provided by BIP!
0
Average
Average
Average
Green