EstherLauraKituyi/Financial-inclusion--Zindi--Challenge

Predicting bank account ownership in East Africa using Machine Learning (Random Forest) ## Financial Inclusion in Africa (Zindi Challenge) ## Project Overview This project aims to predict the likelihood of an individual having a bank account across four East African countries: Kenya, Rwanda, Tanzania, and Uganda. ## The Data The dataset contains demographic information (age, education, job type, etc.) for approximately 33,600 individuals. ## Key Insights - **Digital Access:** Cellphone ownership is a major indicator of financial inclusion. - **Education:** Higher education levels correlate strongly with bank account ownership. - **Top Features:** Age, Education Level, and Household Size were the most important predictors in the model. ## Model Performance - **Algorithm:** Random Forest Classifier - **Baseline Rank:** 1842 on Zindi - **Evaluation:** Focused on improving F1-Score due to class imbalance. ## How to Run 1. Open the `.ipynb` file in Google Colab. 2. Upload `Train.csv` and `Test.csv`. 3. Run all cells.