The rapid growth of IoT technology has revolutionized smart city applications, improving societal functionalities. This integration offers real-time applications for predicting crime events, monitoring environmental conditions, and managing health. However, current IoT-based smart city implementations face challenges in technological capacity and skill readiness. To address this, they propose a framework combining RNN with ALO to predict fire hazard risks early. IoT sensor devices are deployed across smart cities to monitor environmental conditions like drought code, temperature, and humidity. Data is securely stored in Firebase for processing with MATLAB. The model’s effectiveness is validated against conventional methods, demonstrating superior accuracy and minimal errors. This framework addresses technological challenges and offers promising outcomes in predicting and mitigating fire hazards through advanced data analysis.