Optimizing Interior Design

Traditional interior design relies heavily on subjective experience and lacks data-driven support, leading to low efficiency and inconsistent user satisfaction. This study integrates data mining and extension theory to propose a novel intelligent optimization framework for interior design. Using support vector machine (SVM) and decision tree algorithms, the research constructs a hybrid model to extract design rules, optimize spatial layout, and evaluate scheme effectiveness through a weighted fitness function. An office space case shows that the proposed method improves space utilization by 15% and enhances aesthetic and functional performance. Model evaluation indicates the hybrid model achieves 92% accuracy, 90% recall, and 91% F1 score, outperforming single SVM and decision tree models. This integration provides a systematic, data-driven approach to interior design, promoting intelligent transformation and standardized decision-making in the industry.