<p>A comprehensive assessment of the investment attractiveness of Ukraine’s rural areas using a multi-criteria geopolitical analysis based on three key criteria, i.e., natural potential, infrastructure accessibility, and the military security level, was carried out. Additionally, within the natural potential criterion, four main investment directions were considered as sub-criteria, namely, agriculture, renewable (solar and wind) energy, and tourism. To determine the weights of the criteria using the Saaty pairwise comparison method, five large language models (LLMs), namely, GPT-4, Claude, Gemini, Deepseek, and Grok 3, were engaged as virtual experts. It was determined that virtual models exhbit less inconsistancy in their answers than humans. The LLM assessment aligned with the expert opinions on the three key investment attractiveness criteria, but showed lower consensus regarding specific investment directions. Most models identified security as the most important criterion and agriculture as the most attractive investment direction. Six thematic maps and an overall map of the investment attractiveness of Ukrainian villages were created. It was determined that villages in Western Ukraine are more attractive for investment, while those in the East and South are the least attractive ones.</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

Multi-Criterion Analysis of the Investment Appeal of Rural Areas of Ukraine Using Gis and Artificial Intelligence

  • S. Yu. Drozd,
  • N. M. Kussul

摘要

A comprehensive assessment of the investment attractiveness of Ukraine’s rural areas using a multi-criteria geopolitical analysis based on three key criteria, i.e., natural potential, infrastructure accessibility, and the military security level, was carried out. Additionally, within the natural potential criterion, four main investment directions were considered as sub-criteria, namely, agriculture, renewable (solar and wind) energy, and tourism. To determine the weights of the criteria using the Saaty pairwise comparison method, five large language models (LLMs), namely, GPT-4, Claude, Gemini, Deepseek, and Grok 3, were engaged as virtual experts. It was determined that virtual models exhbit less inconsistancy in their answers than humans. The LLM assessment aligned with the expert opinions on the three key investment attractiveness criteria, but showed lower consensus regarding specific investment directions. Most models identified security as the most important criterion and agriculture as the most attractive investment direction. Six thematic maps and an overall map of the investment attractiveness of Ukrainian villages were created. It was determined that villages in Western Ukraine are more attractive for investment, while those in the East and South are the least attractive ones.