regmul/Financial-Inclusion-in-Africa--streamlit-checkpoint-2

This project uses machine learning to predict whether an individual owns a bank account based on their demographic and socioeconomic characteristics. The model is trained on the Financial Inclusion in Africa dataset, which includes data from Kenya, Rwanda, Tanzania, and Uganda. # **💰 Financial Inclusion Prediction App** **🧠 Overview** The Financial Inclusion Prediction App is a machine learning-powered web app built with Streamlit that predicts whether an individual has a bank account based on their demographic and socioeconomic information. The goal of this project is to support data-driven financial inclusion initiatives across Africa by identifying populations with limited access to financial services. **🚀 Features** 🧾 Interactive user input form — Collects demographic and economic details. 🤖 Machine Learning Model — Predicts the likelihood of owning a bank account. 📊 Data Scaling & Encoding — Ensures consistent model input. 🌍 Country Coverage — Kenya, Uganda, Rwanda, and Tanzania. 📈 Deployed using Streamlit — Simple and user-friendly interface. **🧩 Tech Stack** Python 3 Pandas — data processing Scikit-learn — model training and preprocessing Streamlit — web app deployment Pickle — for saving and loading trained models **🧮 Model Description** The predictive model was trained using the Financial Inclusion in Africa dataset from the Zindi Africa Challenge. It uses key features such as: Country Gender Education level Job type Marital status Household size Age Cellphone access Location type The dataset was highly imbalanced (≈86% “No Bank Account” vs 14% “Yes”), so SMOTE (Synthetic Minority Oversampling Technique) was used to balance the classes and improve prediction fairness. ## **🧰 How to Run the App Locally** **1️⃣ Clone this repository:** git clone github.com cd Financial-Inclusion-in-Africa--streamlit-checkpoint-2 **2️⃣ Install dependencies:** pip install -r requirements.txt **3️⃣ Run the Streamlit app:** streamlit run app.py **4️⃣ The app will open in your browser at:** localhost **📦 Project Files** File Description app.py Streamlit web application script financial_data_analysis.pkl Trained machine learning model …