Limited traceability in the food supply chain compromises safety, quality, and operational efficiency, in addition to increasing waste and greenhouse gas emissions. This study presents a software as a service (SaaS) technological solution designed to optimize food traceability and logistics in Mexico’s Food Bank Network. The platform is based on Quick Response (QR), Near Field Communication (NFC), and Internet of Things (IoT) technologies, enabling realtime monitoring of food origin, transportation, status, and delivery by controlling critical variables such as temperature and humidity. A key component of the system is the use of decision tree algorithms, which analyze data collected by IoT sensors to support decision making in the logistics chain. These algorithms structure nodes that represent specific conditions and generate decision paths that trigger automated actions, sending alerts or reassigning distribution routes. Thanks to their ability to manage large volumes of data and their transparent interpretation, decision trees allow for predicting and proactively responding to risk events, improving efficiency and reducing losses. To improve accuracy and mitigate model bias, representative data from all logistics stages were used, along with balanced sampling and cross validation techniques. The results show a 20% to 40% improvement in the proportion of products that remain in optimal condition until their final destination, a 5% to 2% reduction in returns due to moisture, and a 10% increase in operational efficiency. The solution was developed and implemented over six months in a realworld food distribution environment, demonstrating its potential to transform traceability and decision making in food logistics.