Abnormal increases in radon gas (222Rn) concentrations in soil, groundwater, and atmosphere have been consistently observed as precursors of seismic activity, especially near active faults. In this study, we focus on earthquake prediction using IoT-based radon monitoring near the active fault in Manado, North Sulawesi, Indonesia, where seismic activity is high due to interactions between the Eurasian, Pacific, and Philippine plates. Radon gas concentration telemonitoring collected in real-time every minute between October 2023 and August 2024 was analyzed along with seismic data above M4.5 to predict earthquakes with magnitude 4.5 and above. This telemonitoring system enables continuous data storage every minute, with data accessible on the dataalamdiy web server, despite radon concentration readings on the detector updating every 10 minutes to filter out emissions from Thoron and Actanium sources. The results showed that earthquake date prediction sensitivity was 84%, accuracy was 75%, and the average prediction time was 2.65 days before the earthquake. The prediction was based on statistical algorithms derived from the daily average of radon gas concentration fluctuations, which resulted in an effective early warning system. One of the largest earthquakes M6.7 on January 9, 2024, was predicted 2 days ago. These findings highlight the possibility of integrating radon gas concentration anomaly analysis into disaster prevention strategies and provide an important lead time for preparedness efforts in seismically active areas. This research will significantly contribute to earthquake prediction methodology in Indonesia, especially in less-studied areas such as North Sulawesi, improving regional disaster preparedness and resilience.