mini12347/Financial-Inclusion-in-Africa

# 🌍 Financial Inclusion Prediction App ### 🧠 Predicting Bank Account Ownership in Africa using Machine Learning & Streamlit # Dataset source : Zindi Platform --- ## 📘 Overview The **Financial Inclusion Prediction App** is a machine learning web application built to **predict whether a person owns a bank account** based on various demographic and socioeconomic factors such as **country, location type, gender, cellphone access, education level**, and more. This project aims to highlight and analyze the **financial inclusion gap in Africa**, helping policymakers and organizations understand key barriers to banking access. --- ## 🚀 Features - 🤖 **Machine Learning Model (XGBoost):** Classifies individuals as likely or unlikely to have a bank account. - 💻 **Interactive Streamlit Web Interface:** Intuitive UI where users can input details and get instant predictions. - 📊 **Dashboard Page:** Displays interactive charts showing trends and relationships between financial access and demographics. - 🧩 **Data Analysis Notebook:** Includes exploratory data analysis, preprocessing, and model training in Jupyter Notebook. - ☁️ **Deployed Online:** Accessible from any browser via Streamlit Cloud. --- ## ⚙️ Technologies Used | Category | Tools | |-----------|-------| | **Language** | Python 3.12 | | **Libraries** | pandas, numpy,ydata_profiling, plotly, seaborn, matplotlib, scikit-learn, xgboost, joblib, streamlit | | **Tools & Platforms** | Jupyter Notebook, VS Code, Git, GitHub, Streamlit Cloud | --- ## 📂 Project Structure 📁 Financial-Inclusion-Prediction ├── Financial_inclusion_dataset.csv # Dataset .csv ├── Notebook.ipynb # Model training, analysis, and evaluation ├── report.ipynb # ydata_profiling report ├── Stream.py # Streamlit web app ├── xgb_model.pkl # Saved XGBoost model ├── requirements.txt # Project dependencies └── README.md # Documentation --- ## 🧭 Data Description The dataset focuses on **financial inclusion in African countries** and includes columns su …