Bonifacethuo/Financial-Inclusion-in-Africa-Zindi

# Financial-Inclusion-in-Africa-Zindi In this project, the objective was to develop a machine learning model to predict the likelihood of individuals having a bank account (Yes = 1, No = 0) based on demographic data. The dataset provided demographic and financial service usage information for approximately 33,600 individuals across four East African countries: Kenya, Rwanda, Tanzania, and Uganda. The data was split into 70% for training and 30% for testing. Key predictors such as location, gender, education, employment status, and age were analyzed to uncover the factors influencing financial inclusion. A Random Forest Classifier was employed due to its ability to handle categorical data and its robustness in classification tasks. The model aimed to identify individuals most likely to have bank accounts, providing insights into the state of financial inclusion in East Africa. The findings highlight barriers to financial access and suggest potential strategies for enhancing financial security. The model’s accuracy and precision were evaluated on the test set, achieving reliable performance metrics. The insights gained can be used to guide policy decisions and initiatives aimed at improving access to financial services in underrepresented regions, contributing to economic empowerment and growth.