Oginaz/Food-Security-Early-Warning-System-Kenya-Case-Study

This project aims to predict food crises before they occur, enabling timely interventions that reduce the risk of famine and strengthen community resilience. By integrating diverse data sources—including rainfall, food prices, conflict events, and food security assessments—the system provides data-driven early warnings to support decision-makers. # 🌾 Food Security Early Warning System – Kenya Case Study Predicting Food Crises Before They Happen ## 🎯 Problem Statement Food insecurity remains a persistent challenge in Kenya, driven by climate shocks, conflict, and market volatility. National platforms such as the National Information Platform for Food Security and Nutrition (NIPFN) already provide valuable insights by consolidating and reporting on multi-sectoral food security and nutrition data. However, these systems are largely retrospective—they describe the current situation but lack strong predictive capabilities. This creates a critical gap: by the time food crises are formally identified and reported, the opportunity for timely and cost-effective intervention is already limited. Decision-makers—including government agencies, NGOs, and humanitarian actors—require tools that move beyond monitoring and towards forecasting future risks. The Food Security Early Warning System – Kenya Case Study addresses this gap by: 1. Integrating multi-source datasets (rainfall, food prices, conflict events, and IPC phases). 2. Implementing machine learning models (Random Forest, XGBoost) to predict food security phases up to three months ahead. 3. Automating alerts that notify stakeholders when counties are projected to shift into crisis or emergency phases. 4. Providing an interactive dashboard to visualize trends, forecasts, and county-level risks. By complementing existing systems like NIPFN with predictive analytics and early-warning capabilities, this project helps shift Kenya’s food security response from reactive aid to proactive prevention—reducing the severity of crises and strengthening long-term resilience. ## 📌 Project Overview The Food Security Early Warning System – Kenya Case Study is a machine learning–driven solution designed to forecast food security crises up to three months in advance. It builds upon Kenya’s existing monitoring efforts, such as NIPFN, by adding a predictive and proactive layer …