Optimizing Design Education Using Artificial Intelligence: Joint Application of OBE Teaching, Intelligent Color Platform, and BP Neural Network

This study proposes an artificial intelligence-based design education predictive analysis framework that combines outcome-based education (OBE), intelligent color platform, and backpropagation (BP) neural network, aiming to optimize the application of the color composition teaching method. Through a quasi-experimental design with 120 visual communication students, we implemented an OBE-aligned instructional model incorporating the Coolors platform, contrasting it with traditional teaching methods. Quantitative results demonstrated statistically significant improvements in the experimental group, with 7.83-point higher design project scores ([Formula: see text]) and 6.27-point superior theoretical performance ([Formula: see text]) compared to controls. The framework synergizes three components: (a) competency-driven OBE objectives, (b) real-time chromatic feedback via intelligent systems, and (c) BP neural network-based prediction, achieving 2.62% mean error in learning outcome forecasts. Student surveys revealed 71.7% approval for digital tool integration, showing enhanced technical and creative competencies. This study provides an innovative AI-driven teaching model that integrates color theory, educational design, and machine learning, demonstrating predictive analytics’ potential to transform competency-based creative education through data-driven optimization.