Idea
An AI-powered supply chain planning platform that improves inventory accuracy and operational efficiency for large retailers and manufacturers
Research Paper
Core Innovation
This paper presents the SCPA framework that leverages large language models to understand complex supply chain domain knowledge and operator needs. It uniquely decomposes planning tasks and generates interpretable, evidence-based reports that dynamically adjust to environmental changes. This approach improves accuracy and efficiency beyond traditional static planning systems.
Market Size (TAM)
$20–50B TAM, $2–10B SAM; assumption: global supply chain software market with growing AI adoption in retail and manufacturing
Potential Customers & Pain Points
- Large Retailers Facing Inventory Inaccuracy
- Manufacturers Needing Dynamic Supply Chain Adjustments
- Supply Chain Managers Seeking Reduced Labor Costs
- E-commerce Platforms Requiring Real-Time Stock Optimization
Business Model
Subscription-based SaaS platform with tiered pricing based on company size and feature usage
Competitive Landscape
- Llamasoft
- Blue Yonder
- Kinaxis
Implementation Challenges
- Integration with legacy supply chain systems
- Data privacy and security concerns
- Adoption resistance from traditional planners
Validation Strategy
- Pilot deployment with JD.com to measure accuracy and labor reduction
- Collect user feedback to refine interpretability features
- Expand trials to other retail and manufacturing partners
Research Paper Overview
Leveraging LLM-Based Agents for Intelligent Supply Chain Planning
Summary
This paper introduces the Supply Chain Planning Agent (SCPA) framework that utilizes large language models to capture domain knowledge, interpret operator requirements, break down complex tasks, and produce evidence-based planning reports. It is deployed in JD.com's supply chain to enhance plan accuracy, improve stock availability, reduce labor, and dynamically adapt to environmental changes while maintaining interpretability and efficiency.