Workers are more vulnerable to heat stress when working outdoors. Thus, accurate predictions and measures to reduce its effects are crucial. This paper presents a new method that combines Gradient Boosting algorithms with Internet of Things (IoT) technology to combat heat stress, a serious problem for outdoor workers. It uses Gradient Boosting to create a model to predict heat stress levels using several environmental variables, including humidity, temperature, and sun radiation. An IoT sensor is used to gather real-time environmental data, improving the precision and timeliness of heat stress forecasts. By integrating several systems, it may take proactive steps to reduce the potential of heat-related diseases and injuries. These steps include changing work schedules, ensuring people drink enough, and using cooling treatments. The proposed solution uses advanced machine learning (ML) algorithms with IoT infrastructure to dramatically enhance outdoor worker safety in heat-stress-prone situations. It helps preserve outdoor workers' health and well-being by allowing prompt interventions and educated decision-making, leading to successful solutions for anticipating and reducing heat stress. © 2025 Elsevier B.V., All rights reserved.