Scholarlink

<p>To address the structural imbalances and sustainability challenges faced by the sports industry in its high-quality development transformation, and to overcome the shortcomings of existing research in dynamic modeling, multi-objective optimization, and quantitative solutions, this paper constructs an intelligent optimization framework integrating deep learning (DL) and genetic algorithms (GA). This framework uses a one-dimensional convolutional neural network to extract deep features and predict trends from high-dimensional industry data, and employs a genetic algorithm as the optimization engine to find the Pareto optimal solution that synergistically improves economic, social, and environmental benefits. Based on industry statistics from 2010 to 2022 and provincial panel data from 2018 to 2020, the study reveals the core characteristics of the sports industry’s transformation towards service orientation and verifies the impact of the pandemic, which resulted in a 7.2% and 4.6% decrease in total industry output and added value in 2020 compared to 2019, respectively. After adaptation and validation with data from the United States and Germany, the model’s cross-regional prediction error is less than 6%, and the innovation-driven path can increase the proportion of sports services to 68.5% by 2025. This paper breaks through the traditional static description paradigm and provides an intelligent decision-making tool that combines theoretical depth and practical value, offering a new paradigm and empirical support for the precise optimization of industrial structure and cross-regional application.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

RETRACTED ARTICLE: Structural configuration of sustainable sports industry based on deep learning and genetic algorithm

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2025年12月19日

查看全文
  • Yupeng Li,
  • Kitak Kim,
  • Long Zhang

摘要

To address the structural imbalances and sustainability challenges faced by the sports industry in its high-quality development transformation, and to overcome the shortcomings of existing research in dynamic modeling, multi-objective optimization, and quantitative solutions, this paper constructs an intelligent optimization framework integrating deep learning (DL) and genetic algorithms (GA). This framework uses a one-dimensional convolutional neural network to extract deep features and predict trends from high-dimensional industry data, and employs a genetic algorithm as the optimization engine to find the Pareto optimal solution that synergistically improves economic, social, and environmental benefits. Based on industry statistics from 2010 to 2022 and provincial panel data from 2018 to 2020, the study reveals the core characteristics of the sports industry’s transformation towards service orientation and verifies the impact of the pandemic, which resulted in a 7.2% and 4.6% decrease in total industry output and added value in 2020 compared to 2019, respectively. After adaptation and validation with data from the United States and Germany, the model’s cross-regional prediction error is less than 6%, and the innovation-driven path can increase the proportion of sports services to 68.5% by 2025. This paper breaks through the traditional static description paradigm and provides an intelligent decision-making tool that combines theoretical depth and practical value, offering a new paradigm and empirical support for the precise optimization of industrial structure and cross-regional application.