Citas bibligráficas
Gonzalez, B., Mariscal, D. (2024). Improvement proposal based on machine learning, big data and DDMRP to improve forecasting compliance in a consumer goods company [Universidad de Lima]. https://hdl.handle.net/20.500.12724/21467
Gonzalez, B., Mariscal, D. Improvement proposal based on machine learning, big data and DDMRP to improve forecasting compliance in a consumer goods company []. PE: Universidad de Lima; 2024. https://hdl.handle.net/20.500.12724/21467
@misc{renati/1435513,
title = "Improvement proposal based on machine learning, big data and DDMRP to improve forecasting compliance in a consumer goods company",
author = "Mariscal Cruzado, Diana Micaela",
publisher = "Universidad de Lima",
year = "2024"
}
Nowadays, is crucial to accurately forecast products, especially for a company that import its goods. Having an accurate forecasting enables the company to optimize resource management, increasing productivity and preventing overselling or underselling of products. Additionally, establishing a demand-based material planning model is essential to ensure that our suppliers meet their service level commitments. In this research project, Machine Learning and Big Data are employed to enhance de forecasting methods of consumer goods company. The data collected from the company’s sales over the last four years for “the hair category” has been trained and the Arima method will be employed to predict the first 8 months of the year 2023. Furthermore, the Demand Driven Material Requirement Plan (DDMRP) is implemented to improve suppliers service level. The impact of the proposed model will be evaluated using indicators such as Forecast Bias (FB), Forecast Accuracy (FA), Mean Absolute Percentage Error (MAPE) and Service Level Agreement (SLA).
Este ítem está sujeto a una licencia Creative Commons Licencia Creative Commons