Scholarlink

The Public Distribution System (PDS) in India is one of the world’s largest food security programs, serving over 800 million citizens. Yet, the system continues to face critical challenges, including corruption, leakage, and inequitable service delivery. This chapter presents an Agent-Based Model (ABM), developed under the AI FORA (Artificial Intelligence for Fair, Open, and Responsible Automation) initiative, to simulate the complex behavioural and logistical dynamics of the PDS. Implemented in NetLogo, the model incorporates beneficiaries, ration shop operators, suppliers, trucks, and inspectors within a spatially embedded district-level environment. By embedding Responsible AI metrics, the simulation evaluates fairness, transparency, and accountability under varying operational conditions. Scenario-based experiments examine the effects of inspection frequency, corruption propensity, and supply delays on both system efficiency and ethical performance. Findings highlight pathways for digital governance and demonstrate the value of AI-driven simulation as a testbed for designing equitable, accountable, and effective welfare policies.

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

Agent-Based Modelling of the Indian Public Distribution System in AI FORA

  • 章节

  • 出版模式：

    开放获取

  • 发表日期：

    2026年

查看全文
  • Ashly Ann Jo,
  • Ebin Deni Raj,
  • Sumathi Srinivasalu

摘要

The Public Distribution System (PDS) in India is one of the world’s largest food security programs, serving over 800 million citizens. Yet, the system continues to face critical challenges, including corruption, leakage, and inequitable service delivery. This chapter presents an Agent-Based Model (ABM), developed under the AI FORA (Artificial Intelligence for Fair, Open, and Responsible Automation) initiative, to simulate the complex behavioural and logistical dynamics of the PDS. Implemented in NetLogo, the model incorporates beneficiaries, ration shop operators, suppliers, trucks, and inspectors within a spatially embedded district-level environment. By embedding Responsible AI metrics, the simulation evaluates fairness, transparency, and accountability under varying operational conditions. Scenario-based experiments examine the effects of inspection frequency, corruption propensity, and supply delays on both system efficiency and ethical performance. Findings highlight pathways for digital governance and demonstrate the value of AI-driven simulation as a testbed for designing equitable, accountable, and effective welfare policies.