This paper proposes a comprehensive method system integrating linear programming model, fuzzy compromise planning and decision tree algorithm, aiming to optimize the commercial operation and development path of sports industry. By constructing an interactive simulation framework based on the economic indicator model, it supports users to dynamically adjust the objective variables and policy constraints to achieve multi-objective optimization. Aiming at the problem of goal conflict and ambiguity, the affiliation function is introduced to quantify the goal satisfaction, and combined with the payment matrix and global utility function, the multi-objective optimization is transformed into a fuzzy planning problem. The decision tree algorithm CART is further used to optimize feature selection and improve the classification and regression prediction accuracy. Experiments show that the average running time of the CART algorithm is only 165.88 seconds, and the maximum fitness value reaches 1600, which is significantly better than the traditional genetic algorithm (more than 200 seconds) and ID3 and C4.5 algorithms. Based on the 2015-2024 sports industry data, the model consistency test shows that the simulation error of the total revenue of the sports industry is lower than 3.32%, and the error of the event-related revenue is generally lower than 6%, which verifies the effectiveness of the model. The sensitivity analysis shows that a 30% increase in the proportion of government financial support can increase the total revenue of the sports industry to 7.40 trillion yuan (+30.8%) in 2024, and a 30% increase in the proportion of sponsor investment can drive the revenue to 8.20 trillion yuan (+44.9%). The study provides data-driven decision support for sports industry resource allocation, risk analysis and policy formulation.
