Gbadet/Nigeria-Transport-Cost-Project-ML

A machine learning project focused on uncovering structural transport cost patterns across Nigeria to support data-driven policy decisions. # 🚍 Nigerian Transport Cost Optimization A machine learning project focused on uncovering structural transport cost patterns across Nigeria to support data-driven policy decisions. --- ## 📌 Problem Statement Traditional analysis of transport costs relies on national averages, which hide regional disparities. This project aims to identify underlying cost patterns across states for more targeted and effective interventions. --- ## ⚙️ Methodology - **Data Source:** NBS Transport Cost Watch (Oct 2024) - **Preprocessing:** Data normalization for cross-mode comparison - **Clustering:** K-Means to group states by cost structure - **Dimensionality Reduction:** PCA for visualization and pattern clarity --- ## 🔍 Key Findings - Identified **4 distinct transport cost clusters** across Nigeria: - **Low-Cost Stability** - **High-Fare Pressure** - **Water-Cost Heavy** - **Intracity Cost Intensity** - Significant regional differences exist across transport modes - Water transport costs heavily impact riverine states - Urban areas show high intracity commuting pressure --- ## 📊 Impact - Moves analysis beyond averages to **structure-based insights** - Enables **targeted policy interventions** instead of blanket approaches - Supports **evidence-based planning** in transportation and infrastructure --- ## 🧠 Recommendations - Implement **mode-specific subsidies** (e.g., water transport, aviation) - Invest in **urban mass transit systems** - Establish **continuous monitoring systems** for transport cost trends --- ## 🛠️ Tools & Technologies - Python - Power Point --- ## 📈 Project Outcome A data-driven framework for understanding transport cost dynamics and guiding strategic decision-making at regional and national levels.