cynthiakemboi/Machine-learning-Model-on-Refugee-Population-Forecasting-Resource-Planning-System-for-Kenya
Domain:
socioeconomicRecord type:
project
Creator:
cyn
Host:
Kenya hosts refugee and asylum-seeking populations from multiple countries affected by conflict, political instability, economic crises, and natural disasters. Humanitarian agencies often face challenges in forecasting refugee population changes, resulting in resource shortages or inefficient allocation of aid.
# 🇰🇪 Kenya Refugee Population Forecasting and Humanitarian Resource Planning System
A machine learning-powered decision support system that forecasts refugee and asylum-seeker populations in Kenya and translates those predictions into estimated humanitarian resource requirements, including food, shelter, healthcare, and education.
---
## 🌐 Live Application
**Streamlit App**
---
# 📑 Table of Contents
* Project Overview
* Business Problem
* Project Objectives
* Dataset
* Repository Structure
* Project Workflow
* Key Findings
* Feature Engineering
* Model Development
* Model Performance
* Why FT-Transformer?
* Streamlit Application
* Technology Stack
* Installation
* Running the Project
* Business Insights
* Limitations
* Future Improvements
* Contributors
* References
* Acknowledgements
* License
---
# 📖 Project Overview
Kenya hosts hundreds of thousands of refugees and asylum seekers displaced by conflict, persecution, political instability, and climate-related disasters across East and Central Africa.
Humanitarian organizations often depend on historical population reports when allocating resources, making it difficult to respond proactively to sudden population increases.
This project applies machine learning and deep learning techniques to forecast refugee populations and estimate humanitarian resource requirements before crises escalate.
The project follows the **CRISP-DM (Cross-Industry Standard Process for Data Mining)** methodology, from business understanding through deployment.
---
# 🎯 Business Problem
Population movements can change rapidly because of:
* Armed conflicts
* Political instability
* Climate shocks
* Economic crises
* Humanitarian emergencies
These fluctuations create uncertainty in planning for:
* Food distribution
* Shelter allocation
* Healthcare services
* Educational support
* Water and sanitation
Without predictive analytics, humanitarian agencies risk delayed responses, inefficient resource allocation, and inc …
Similar
Development of a machine learning model for precipitation forecasting in KenyaReport on the development of a machine learning forecasting system for NDVI: A case study for Kenya.Machine learning for earth system observation and forecastingApplication of Sales Forecasting Model Based on Machine Learning Algorithms.Machine Learning Models for Climate Prediction and Adaptive Planning in KenyaStatistical, machine learning, and deep learning models for COVID-19 forecasting in Kenya