| In recent years, the extensive application of recommender systems in fields such as e-commerce and streaming services has significantly enhanced user experiences. While traditional recommendation methods have effectively improved user satisfaction, they exhibit shortcomings in balancing platform revenue and provider fairness in multi-objective optimization scenarios. To address these challenges, we propose a fairness-aware multi-objective optimization framework solved using intelligent evolutionary algorithms. Specifically, the framework integrates three core metrics: user satisfaction, provider fairness, and platform revenue, and applies an improved genetic algorithm (GA) for single-objective optimization. Furthermore, the non-dominated sorting genetic algorithm (NSGA) is introduced to optimize multiple objectives simultaneously, maintain solution diversity, and avoid biases introduced by weight assumptions. Finally, experiments on various real-world datasets demonstrate that the proposed method outperforms existing recommendation algorithms regarding user satisfaction, provider fairness, and platform revenue. |
