Technological developments and the expansion of urban data have forced traditional urban service management practices to move towards smart, data-driven, and predictive management. The quality of urban services, as one of the most important aspects of urban management performance, is influenced by several factors, including infrastructure quality, citizen demand, operational capacity, environmental conditions, spatial characteristics, and resource allocation. In the meantime, artificial intelligence with its ability to process large data, discover complex patterns, and predict future situations can pave the way for changing urban service management from a reactive to a predictive approach. The present study aimed to design an intelligent model for predicting and managing urban service quality based on artificial intelligence in the city of Ahvaz. The research is applied in terms of purpose and exploratory in terms of method, and in the model design section, it is based on a systematic review of the literature and content analysis of related studies. In the first stage, the literature related to urban service quality, smart city, artificial intelligence, machine learning, and data-driven management was reviewed. Then, the components affecting the quality of urban services and the requirements for the use of artificial intelligence were extracted and classified into conceptual dimensions. The analysis results showed that the smart model of urban service quality can be designed based on five main dimensions including data quality and integrity, artificial intelligence capabilities, spatial and environmental characteristics, managerial and operational capacity, and perceived quality and actual performance of services. Based on the proposed model, citizen, operational, spatial, environmental, and infrastructure data are entered into the system and, after processing, the probability of service quality decline is predicted using machine learning algorithms. Then, the prediction output is transferred to the management intervention prioritization system in the form of a spatial-temporal risk index.