Optimización para el transporte de contenedores reefer de un Operador Logístico en Perú.
Average rating
Cast your vote
You can rate an item by clicking the amount of stars they wish to award to this item.
When enough users have cast their vote on this item, the average rating will also be shown.
Star rating
Your vote was cast
Thank you for your feedback
Thank you for your feedback
Issue Date
2025-06-16Keywords
Logística internacionalTransporte refrigerado
Machine learning
Exportación perecible
Planificación predictiva
International logistics
Refrigerated transport
Machine learning
Perishable exports
Predictive planning
Metadata
Show full item recordOther Titles
Optimization of Reefer Container Transport for a Logistics Operator in PeruAbstract
El presente trabajo analiza la problemática relacionada con la escasez de unidades de transporte refrigerado (Reefer) durante las temporadas de alta demanda de exportación en productos perecibles como palta, uva, arándano y cítricos. Esta situación genera sobrecostos operativos, retrasos logísticos y riesgos de pérdida comercial para los exportadores. El estudio se desarrolla en el contexto de un operador logístico nacional que enfrenta limitaciones estructurales y de planificación ante el incremento estacional de la demanda. Se plantearon tres alternativas tecnológicas para resolver la problemática: 1) implementación de un modelo de análisis predictivo de demanda, 2) incorporación de algoritmos de Machine Learning como complemento al sistema actual, y 3) migración al sistema IBM SCIS con OTM con inteligencia artificial integrada. A través de entrevistas, matriz de selección, cronograma de implementación y análisis financiero, se evaluaron los beneficios, riesgos e implicancias de cada alternativa. La alternativa elegida fue la incorporación de Machine Learning, por su rápida aplicabilidad, bajo costo inicial y potencial para optimizar recursos logísticos anticipadamente. Se concluye que esta solución no solo responde a la problemática operativa, sino que ofrece una ventaja competitiva al permitir negociaciones estratégicas, mayor previsibilidad y mejor desempeño en indicadores OTIF (On Time, In Full) durante las campañas de exportación.This study analyzes the issue related to the shortage of refrigerated transport units (reefers) during peak export seasons for perishable products such as avocado, grape, blueberry, and citrus fruits. This situation leads to operational cost overruns, logistical delays, and commercial loss risks for exporters. The research is conducted in the context of a national logistics operator facing structural and planning limitations in response to the seasonal surge in demand. Three technological alternatives were proposed to address the issue: Implementation of a predictive demand analysis model, Integration of Machine Learning algorithms as a complement to the current system, and Migration to IBM Supply Chain Intelligence Suite (SCIS) with OTM and integrated artificial intelligence. Through interviews, a selection matrix, an implementation timeline, and financial analysis, the benefits, risks, and implications of each alternative were evaluated. The chosen alternative was the integration of Machine Learning due to its rapid applicability, low initial cost, and potential to proactively optimize logistics resources. The study concludes that this solution not only addresses the operational challenge but also provides a competitive advantage by enabling strategic negotiations, greater predictability, and improved performance in OTIF (On Time, In Full) indicators during export campaigns.
Type
info:eu-repo/semantics/bachelorThesisRights
info:eu-repo/semantics/openAccessLanguage
spaCollections


