EngIbrah/Financial-Inclusion-in-Africa-Zindi-Competition

# Financial Inclusion in Africa — Zindi Competition 📊 **Short description** This repository contains code and data used for the Zindi competition "Financial Inclusion in Africa." The goal is to predict whether a person has access to financial services using demographic and socio-economic features. --- ## 🔍 Project overview - **Competition**: Zindi — Financial Inclusion in Africa - **Task**: Binary classification to predict financial inclusion - **Notebook**: `fincial_inclusion_in_africa_notebook.ipynb` contains EDA, preprocessing, modeling experiments, and submission generation steps. --- ## 📁 Repository structure - `fincial_inclusion_in_africa_notebook.ipynb` — main analysis and modelling notebook - `data/` — dataset folder - `Train.csv` — training set with labels - `Test.csv` — test set for which submissions are generated - `VariableDefinitions.csv` — variable descriptions - `SampleSubmission.csv` — sample submission format - `submissions/` — generated submission files (example outputs) --- ## 🧰 Requirements & setup Recommended Python environment (example): ```bash python -m venv .venv # Windows PowerShell .\.venv\Scripts\Activate.ps1 pip install --upgrade pip pip install -r requirements.txt ``` Minimum suggested packages (add exact versions in `requirements.txt`): - pandas - numpy - matplotlib - seaborn - scikit-learn - xgboost - lightgbm (optional) - jupyterlab or notebook Note: The notebook contains a `pip install xgboost` cell — add `xgboost` to your `requirements.txt` to avoid installing from inside the notebook. --- ## ▶️ How to run 1. Activate your Python environment 2. Install dependencies: `pip install -r requirements.txt` 3. Open the notebook: ```bash jupyter lab # or jupyter notebook ``` 4. Run notebook cells in order (EDA → preprocessing → modeling → generate submission) 5. Generated submissions are saved to `data/submissions/` (e.g. `second_submission.csv`) --- ## 🧾 Notebook summary & findings 🔎 - **Preprocessing**: implemented i …