Celestine-Glitse/Financial-Inclusion-in-Africa

This project aims to create a machine learning model to predict which individuals are most likely to have or use a bank account, which serves as an indicator of financial inclusion in Kenya, Rwanda, Tanzania, and Uganda. The goal is to understand the key factors that drive individuals' financial security. # Financial Inclusion in Africa - Machine Learning Classification Project ## Project Overview This project aims to predict which individuals in Kenya, Rwanda, Tanzania, and Uganda are most likely to have or use a bank account. The ability to access bank accounts is a critical indicator of financial inclusion and economic development. This project uses machine learning techniques to provide insights into the factors that drive financial security across these countries. ## Table of Contents - Project Overview - Data - Features - Models Used - Evaluation Metrics - Installation - Usage - Results - Contributing - License ## Data The dataset used in this project contains information on individuals across Kenya, Rwanda, Tanzania, and Uganda. The key target variable is `bank_account`, which indicates whether an individual has access to or uses a bank account. ### Key Variables: - **Country**: The country of residence. - **Year**: The year of data collection. - **Unique ID**: An identifier for each individual. - **Education Level**: The education level of the respondent. - **Age of Respondent**: The age of the individual. - **Job Type**: The type of job the respondent holds. - **Marital Status**: The marital status of the individual. - **Gender**: The gender of the individual. ## Features The project employs various features, including demographic, socioeconomic, and geographic variables, to predict financial inclusion. ## Models Used This project explores various machine learning models, including: - Logistic Regression - Random Forest Classifier - Support Vector Machine (SVM) - XGBoost Classifier ## Evaluation Metrics The following metrics were used to evaluate the models: - **Accuracy**: The proportion of correct predictions. - **Mean Absolute Error (MAE)**: The average absolute differences between the predicted and actual values. MAE clearly indicates how close predictions are to the actual outcomes on average, with lower values indicating better performance …