AhmedEltokhy5011/Streamlit_Africa_Financial_Inclusion

Predict financial inclusion in African countries using a Random Forest model. The project includes data analysis, preprocessing, model training, and a Streamlit web app for predictions. Technologies: Python, Pandas, Scikit-Learn, Streamlit. Explore the interactive app to gain insights and make informed decisions. # Streamlit Africa Financial Inclusion Prediction ### Project Overview This project aims to predict financial inclusion in African countries using a machine learning model. Financial inclusion, which refers to the access and use of financial services by individuals, is crucial for economic development. By leveraging data from various African countries, this project seeks to identify the factors influencing financial inclusion and predict whether an individual has a bank account. ### Key Features - Data Analysis and Preprocessing: Comprehensive data analysis and preprocessing, including handling missing values, encoding categorical variables, and identifying outliers. - Machine Learning Model: A Random Forest Classifier is trained to predict financial inclusion, achieving an accuracy of 86%. - Streamlit Web Application: An interactive web application built using Streamlit to allow users to input data and get predictions on financial inclusion. - Visualization: Data visualizations to help understand the distribution and relationships of key variables. ### Technologies Used - **Python:** For data analysis, preprocessing, and model building. - **Pandas:** For data manipulation and analysis. - **Seaborn & Matplotlib:** For data visualization. - **Scikit-Learn:** For machine learning model implementation. - **Streamlit:** For building the web application. - **Git & GitHub:** For version control and project sharing. ### Files Included - **main.py:** Contains data loading, preprocessing, model training, and evaluation. - **tuning.py:** Hyperparameter tuning for the Random Forest model using GridSearchCV. - **streamlit_app.py:** The Streamlit application for predicting financial inclusion. - **requirements.txt:** List of all required packages and their versions. - **model.pkl:** Serialized machine learning model. - **df_encoded.pkl:** Encoded dataframe used for model training. - **UNUZ4zR - Imgur.jpg:** Image used in the Streamlit application. ### How to Run - Clone the …