Abstract: As a key pillar of energy transition, offshore wind power relies heavily on cost control and marketing management, both of which directly affect project profitability and competitiveness. However, traditional approaches fail to capture their complex coupling and dynamic feedback mechanisms. To address this gap, this study employs deep learning to investigate the correlation between cost control and marketing management in offshore wind projects. A cost-marketing correlation model is constructed, integrating nonlinear feature extraction, cross-domain weight allocation, and robust objective optimization to systematically analyze cost deviation evolution and pricing response. Using historical data from an actual offshore wind farm as a pilot test, results demonstrate that the proposed method significantly improves predictive accuracy and robustness, thereby providing theoretical reference for investment decision-making, risk management, and marketing strategy optimization in offshore wind projects.