Optimizing green supply chain circular economy in smart cities with integrated machine learning technology

Area of Science:

• Environmental Science
• Computer Science
• Economics

Background:

• Integrating green supply chain and circular economy principles is crucial for smart city sustainability.
• Accurate prediction models are needed to guide economic development efficiency.

Purpose of the Study:

• To enhance green supply chain circular economy integration in smart cities using machine learning.
• To optimize prediction model parameters with the gravitational algorithm for improved accuracy.

Main Methods:

• Developed a nationwide prediction model using economic, environmental, and demographic data.
• Employed support vector machine (SVM) optimized by the gravitational algorithm.
• Conducted empirical analysis to evaluate model performance.

Main Results:

• Achieved minimal mean squared error (0.007) and root mean squared error (0.103).
• Recorded a low mean absolute percentage error of 0.0923.
• Observed reduced prediction error and standard deviation with model optimization, indicating convergence and accuracy.

Conclusions:

• Machine learning, particularly SVM optimized with gravitational algorithm, significantly enhances prediction accuracy for green supply chain circular economy efficiency.
• The model offers valuable insights for sustainable development decision-making.