pxprosper/Financial-inclusion-in-Africa-challenge

Machine learning model to predict which individuals are most likely to have or use a bank account. providing an indication of the state of financial inclusion in Africa, while providing insights into some of the key factors driving individuals’ financial security. # Financial Inclusion in Africa Challenge Machine learning model to predict which individuals are most likely to have or use a bank account. This provides an indication of the state of financial inclusion in Africa, while offering insights into some of the key factors driving individuals' financial security. ## 📌 Overview Financial inclusion remains a critical development challenge in Africa. This project uses data science to understand the key socio-economic factors that influence an individual's access to formal financial services. By predicting bank account ownership, we can help identify populations that are underserved and potentially guide targeted interventions. ## 📊 Dataset The dataset for this challenge is sourced from the **Zindi Financial Inclusion in Africa Challenge**. It contains demographic information and financial service access details for individuals across several East African countries. * Source: (Zindi Africa (Competition P…) - A platform for data science competitions in Africa. * Target Variable: Indicates whether an individual has a bank account. ## 🧠 Model Approach * Model Selected: RandomForestClassifier * Evaluation Metric: Accuracy, AUC.(the metric used by Zindi) ## 📈 Results The final model was evaluated and predictions were submitted to the Zindi competition. * Public Leaderboard Score: 0.110 The submission file `submission.csv` contains the predictions formatted according to competition requirements.