The city of Jeddah recently experienced severe flooding, significantly impacting the community. We employed data mining techniques such as classification and association rules to investigate the complex relationships between large-scale atmospheric teleconnections and extreme precipitation events in Jeddah. Our study focused on classifying and analyzing the surrounding sea surface temperatures (SSTs) of the Mediterranean, Red, Arabian, and Gulf seas, along with the Southern Oscillation Index (SOI), Oceanic Nino Index (ONI), and monthly precipitation data for Jeddah. This analysis aims to identify the most significant factors and extract important nonlinear features from long-term measured data from 1970 to 2024. We applied our approach to varying lag times and evaluated the accuracy of the results based on confidence values. The findings revealed hidden associations between detrended SSTs and major extreme precipitation events, including floods in November 2009, December 2010, and January 2011. An extracted rule revealed that the 2017 flood event was associated with the La Nina phenomenon, low detrending of SSTs in the Red and Arabian Seas, and very low detrending of Gulf SSTs concurrently. This approach could serve as a valuable tool for decision-makers, providing knowledge-driven insights to help mitigate the risk of flooding. Practical implications: Flood disasters have become increasingly frequent and destructive due to the impacts of climate change, particularly in semiarid and arid regions such as the Kingdom of Saudi Arabia. The consequences of these events are significant, posing risks to human lives and leading to substantial economic losses. However, predicting floods in the region remains challenging, as precipitation is the primary driver of these disasters. Large-scale ocean-atmospheric teleconnections can influence hydroclimatic events across vast distances globally. Understanding the complex associations between these teleconnections and extreme precipitation is critical for the region. This study employed hybrid data mining techniques to explore the nonlinear relationships between extreme precipitation events and large-scale ocean-atmospheric signals, using Jeddah city as a case study. The results revealed several rules that shed light on the hidden nonlinear characteristics of extreme precipitation events and their connection to large-scale teleconnections. Therefore, the practical implications of this study can be summarized as follows: - This approach can be a strong tool for decision-makers, allowing them to make informed, proactive decisions to mitigate extreme precipitation events. - Adaptation strategies to lessen the impacts of extreme hydroclimatic events in the region can be developed based on this research.