cherotichfaith-data/PREDICTION-USING-LINEAR-REGRESSION

This repository contains my prediction for who has or have access to a bank account in East Africa countries(Kenya, Uganda, Tanzania and Rwanda) # Financial Inclusion in East Africa A Machine learning project examining financial inclusion across Kenya, Rwanda, Tanzania, and Uganda to predict bank account ownership and identify key demographic factors influencing financial outcomes. ## 📋 Table of Contents - Project Overview - Dataset - Installation - Usage - Methodology - Results - Model Performance - Contributing - License ## 🎯 Project Overview This project addresses the challenge of financial inclusion in East Africa. Financial inclusion remains one of the main obstacles to economic and human development in the region, with only 13.9% of the adult population having access to or using a commercial bank account across Kenya, Rwanda, Tanzania, and Uganda. ### Research Question Predict which individuals are most likely to have or use a bank account, while providing insights into the state of financial inclusion in Kenya, Rwanda, Tanzania, and Uganda. ### Success Metric The model is considered successful if it can accurately identify demographic factors that drive financial outcomes and provide meaningful insights into financial inclusion patterns. ## 📊 Dataset - **Source**: Various Finscope surveys (2016-2018) - **Creators**: Financial Sector Deepening organizations across East Africa - **Generated**: 2016-2018 - **Size**: 23,524 individuals with 13 features - **Features**: - Demographic information (age, gender, education level) - Household characteristics (size, relationship with head) - Geographic indicators (country, location type) - Economic factors (job type, marital status) - Technology access (cell phone access) - Target variable: bank account ownership (Yes/No) ### Dataset Characteristics - **Missing values**: Initially contained missing values across multiple columns (handled during preprocessing) - **Class distribution**: 14.1% with bank accounts, 85.9% without bank accounts - **Data cleaning**: Null values removed, column names standardized, anomalies in year column addressed ## 🛠 Installa …