Repository logo
Communities & Collections
All of DSpace
  • English
  • العربية
  • বাংলা
  • Català
  • Čeština
  • Deutsch
  • Ελληνικά
  • Español
  • Suomi
  • Français
  • Gàidhlig
  • हिंदी
  • Magyar
  • Italiano
  • Қазақ
  • Latviešu
  • Nederlands
  • Polski
  • Português
  • Português do Brasil
  • Srpski (lat)
  • Српски
  • Svenska
  • Türkçe
  • Yкраї́нська
  • Tiếng Việt
Log In
New user? Click here to register. Have you forgotten your password?
  1. Home
  2. Browse by Author

Browsing by Author "Arce Campoverde, Jeniffer Mishelle"

Filter results by typing the first few letters
Now showing 1 - 1 of 1
  • Results Per Page
  • Sort Options
  • No Thumbnail Available
    Item
    Desarrollo de un Modelo Predictivo Inteligente para la Gestión de la Bodega General de una Industria Láctea mediante Redes Neuronales
    (Universidad de Cuenca. Facultad de Ciencias Químicas, 2026-02-19) Arce Campoverde, Jeniffer Mishelle; Fajardo Parra, Kevin Fernando; Flores Sigüenza, Pablo Andrés
    The Ecuadorian dairy industry is a strategic pillar of the national agri-food system, as it integrates productive chains that generate employment, added value, and a continuous supply of essential goods. However, deficiencies in inventory management and supply planning affect the operational efficiency of companies in the sector by creating imbalances between material availability and actual production requirements. In response to this problem, this study proposes the development of a predictive model for supply requirements based on machine learning and artificial neural networks, aimed at optimizing the management of the general warehouse of a dairy company located in Cuenca. The methodology was structured in three phases: a systematic literature review and initial diagnosis; the construction of the predictive model through the comparison of neural network architectures; and the evaluation of the model under alternative consumption scenarios to analyze its sensitivity and stability, along with the formulation of improvement recommendations. The results show that the hybrid MLPLSTM model improves forecasting performance compared with traditional models, especially in highly intermittent consumption series, achieving an adequate conditional mean absolute error and good generalization. In conclusion, the proposed model provides a technological tool to reduce overstock, prevent stockouts, and strengthen logistics efficiency and sustainability.

DSpace software copyright © 2002-2026 LYRASIS

  • Privacy policy
  • End User Agreement
  • Send Feedback