NickIssacs01/Conflict_Prediction_Model_for_Africa

This is a group project to come up with the best model that will be able to predict conflict in Africa. the model will be able to help future investors, to invest more on the continent by avoiding conflict prone areas. # **ANALYZING AFRICA'S CONFLICT LANDSCAPE TO INFORM BUSINESS INVESTMENTS** # **BUSINESS UNDERSTANDING** Africa is highly marketable to multinationals due to its vast natural resources, growing consumer market, and expanding economic opportunities. However conflict and Political instability can lead to supply chain disruptions, regulatory hurdles, and heightened security expenses, making it difficult for businesses to operate efficiently. Using a structured data driven approach, this project used the data set to; 1. Investigate insights on key risk factors causing the conflict, event forecasting, conflict risk score, and risk classification. 2. Analyze the data set to identify conflict prone areas, forecast conflict areas, establish conflict score for countries, risk classification for different countries. 3. Perform statistical tests to understand which areas are prone to conflict, their risk scores, forecast areas in future likely to experience conflict and classify different types of conflict. 4. Provide actionable recommendations to multinationals on conflicts in Africa in terms of areas prone to conflicts and types of conflict so they can formulate good risk management strategies. # **Problem Statement** A UK based multinational organization (VMagic Leather Processing Factory) is interested in establishing a manufacturing plant in a location that is less prone to conflict and political instability. The organization has hired our data science consulting firm to analyze data for different countries in Africa and come up with a model that can accurately determine conflict hot spots and forecast conflict events. # **Objectives** 1) Conduct a comprehensive conflict analysis in Africa by establishing a foundational understanding of conflict types, high-risk regions, and underlying causes 2) Explore the dataset to gain familiarity with its structure, terminology, and quality by examining key variables, including numerical and categorical data. 3) Provide business i …