Agricultural Market Location Selection Using Genetic Algorithm

A study by Guizhe Xin, published in April 2026, presents a methodology for selecting locations for Agricultural Product Wholesale Markets. The research integrates Geographic Information System (GIS) data, national planning resources, and urban big data into a unified database. It applies a Genetic Algorithm implemented in Python to optimize location selection criteria, validated through a case study with seven candidate schemes.

Use Cases

• Optimizing market location by integrating GIS-based criteria like road traffic planning and land use.
• Applying a Genetic Algorithm to re-optimize combined subjective (AHP) and objective (entropy) weight calculations for decision-making.
• Ranking candidate locations using a five-phase methodology involving region screening, scope delineation, and data analysis.
• Validating location selection frameworks for other large-scale infrastructure projects using the provided methodological approach.

Strengths

• Methodology validated through a concrete case study evaluating seven candidate location schemes.
• Integrates multiple data sources including national territorial planning and urban big data via GIS technology.

Limitations

• The dataset is very small at 16.0 KB, indicating it contains code and documentation rather than extensive raw data.
• No sample data or column information is provided, limiting immediate analysis of the underlying evaluation data.

Provenance

Source

Guizhe Xin via figshare.

Collection Method

Research synthesis integrating GIS data, planning documents, and algorithmic optimization.

Freshness

Last updated in April 2026.

Geography

Methodology is general but demonstrated with a case study; specific geographic scope is not stated.