Student4C/Smart-Supply-Chain-for-Sustainable-Oils

This project uses Artificial Intelligence to optimise the distribution of organic, cold-pressed oils from Kenya to global markets. # Smart-Supply-Chain-for-Sustainable-Oils Artificial Intelligence to optimise the distribution of organic oils from Kenya to global markets. ## Summary This project uses Artificial Intelligence to optimize the distribution of organic, cold-pressed oils from Kenya to global markets. By predicting demand, improving logistics, and minimizing waste, the system supports both sustainability and charity funding for destitute children in Kenya. Background The export and distribution of high-quality Kenyan oils face frequent challenges such as inconsistent logistics, unstable demand, and limited transparency. These inefficiencies increase costs and reduce profits that could otherwise fund community programs for children in need. This project combines my passion for sustainability and social impact. I run a business that distributes organic oils and funds a charity for children in Kikambala, Kenya. By integrating AI, I hope to make our supply chain smarter, reduce losses, and increase funds for education and food programs. Problems solved: Unpredictable market demand Transportation inefficiencies High operational costs reducing charity funding How is it used? The AI system uses predictive analytics to forecast demand in different markets and recommends optimal shipping routes based on real-time data such as weather, port congestion, and pricing trends. Users include: Export managers who plan shipments Logistics teams coordinating deliveries Charity administrators monitoring funds generated from sales Data sources and AI methods Data sources: Historical export and sales records from Kenya and the UK Real-time logistics and shipping data (APIs) Market price and seasonal demand data from online marketplaces AI methods: Regression models for price prediction Time-series forecasting for demand planning Optimization algorithms for route and cost minimization Neural networks for dynamic supply-demand matching Challenges Limited availability of clean, consistent data from dev …