YusufBolaji/Agricultural_Supply_Chain_Analysis

An end-to-end data analytics project analyzing agricultural supply chain performance, post-harvest losses, revenue, transportation, and market efficiency in Nigeria. # Agricultural Supply Chain Analysis ## Project Overview This project presents an end-to-end data analysis of agricultural supply chain activities across multiple states in Nigeria. The analysis focuses on crop performance, post-harvest losses, agricultural revenue, market pricing, transportation efficiency, storage practices, and profitability. The goal of the project is to transform agricultural supply chain data into meaningful insights that can support farmers, cooperatives, agribusinesses, and decision-makers in improving supply chain efficiency and profitability. ## Business Problem Agricultural supply chains face several operational challenges, including post-harvest losses, transportation delays, inadequate storage facilities, and differences between farm-gate and market prices. This project analyses agricultural supply chain data to identify performance patterns, operational inefficiencies, and opportunities for improving agricultural profitability. ## Project Objectives The analysis aims to: * Evaluate agricultural revenue across crops and states. * Analyse post-harvest losses by crop. * Examine market price trends over time. * Assess transportation efficiency. * Evaluate the role of storage practices in revenue performance. * Compare cooperative members and non-members. * Analyse crop price margins and profitability. * Identify high-performing crops and regions. * Provide practical business recommendations. ## Dataset Overview The dataset contains **70,000 agricultural supply chain records and 21 variables**. Key fields include: * Crop * State * Local Government Area (LGA) * Harvest Date * Season * Quantity Harvested * Post-Harvest Loss Percentage * Quantity Sold * Farm-Gate Price * Market Price * Gross Revenue * Transport Mode * Transport Cost * Destination Market * Days to Market * Storage Type * Fertilizer Usage * Irrigation Usage * Cooperative Membership ## Tools Used * **Python:** Data cleaning, feature engineering, exploratory data an …