Optimización del stock de los productos de Toalco mediante un algoritmo K-means.

Abstract

Efficient inventory management is fundamental to corporate competitiveness today, as innovation and process automation—driven by data analysis—have become effective tools for improving product classification by identifying the variables that directly influence product behavior. Nevertheless, understanding and applying machine learning concepts—such as Principal Component Analysis and the K-Means algorithm for product segmentation—remain a challenge. The classification of products and the identification of the variables that affect their turnover and cost within the inventory are of primary importance, as they allow companies to adopt new procurement strategies and reduce the risks of overstock and stockouts. The present research focuses on developing a methodology based on Principal Component Analysis and the K-Means algorithm for the segmentation of inventory products, with the aim of achieving a representative grouping of products according to their demand, cost, and turnover behavior. The application of Principal Component Analysis and the K-Means algorithm for this segmentation is justified given that inventory management constitutes one of the most decisive operational processes for the profitability and efficiency of companies, as it represents a significant share of their working capital.