cliffordnwanna/FINANCIAL_INCLUSION_PREDICTION_APP

The Financial Inclusion Prediction project predicts bank account ownership among individuals in East Africa using demographic data. Built with Streamlit and powered by a Random Forest Classifier, the app provides instant predictions based on user inputs, addressing financial accessibility for approximately 33,600 individuals. # **Financial Inclusion Prediction App** ## **Overview** The **Financial Inclusion Prediction** project aims to predict whether individuals in East Africa are likely to have a bank account based on demographic information and various financial service usage patterns. Utilizing a machine learning model, this application helps identify individuals who may benefit from targeted financial services, contributing to increased financial inclusion across the region. ## **Dataset Description** The dataset contains demographic information for approximately **33,600 individuals** across East Africa, detailing their access to financial services. It includes variables such as age, gender, education level, and relationship with the head of the household. **Dataset Link**: Financial Inclusion Dataset ### **Variable Definitions** - **country**: Country of the interviewee. - **year**: Year the survey was conducted. - **uniqueid**: Unique identifier for each interviewee. - **location_type**: Type of location (Rural, Urban). - **cellphone_access**: If the interviewee has access to a cellphone (Yes, No). - **household_size**: Number of people living in the household. - **age_of_respondent**: Age of the interviewee. - **gender_of_respondent**: Gender of the interviewee (Male, Female). - **relationship_with_head**: Relationship with the head of the household. - **marital_status**: Marital status of the interviewee. - **education_level**: Highest level of education attained. - **job_type**: Type of job held by the interviewee. - **bank_account**: Target variable indicating whether the interviewee has a bank account. ## **Project Structure** ``` Financial-Inclusion-Prediction/ │ ├── data/ # Directory for storing datasets │ └── Financial_inclusion_dataset.csv # Dataset file (optional: download via script) │ │ ├── models/ # Directory for trained models │ └── streamlit_trained_model.sav # Trained machine learning model file │ ├── …