The integration of artificial intelligence (AI) and machine learning (ML) into information system design has transformed data management, analytics, and decision-making processes. This paper presents a comprehensive framework that leverages AI and ML techniques to address challenges related to data quality and analytical precision in modern information systems. By focusing on key areas such as data preprocessing, anomaly detection, and predictive modeling, the framework achieves significant improvements in accuracy, consistency, and reliability. Results demonstrate that missing value handling improved from 78 to 96%, noise reduction increased from 82 to 94%, and data consistency rose from 80 to 97%. Predictive models exhibited enhanced performance, with neural networks achieving an accuracy of 95% and the lowest validation loss of 0.11. A case study approach validates the framework’s efficacy, showcasing improved decision-making and operational efficiency. The framework is adaptable and scalable, making it suitable for diverse industries such as healthcare, finance, and supply chain management. This research advances the design of intelligent information systems capable of transforming raw data into actionable insights, enabling more effective and reliable decision-making processes.