This project analyzes user reviews of banking applications to extract insights and trends.

banking-reviews/
├── data/               # Raw and processed data
│   ├── raw/           # Original, immutable data
│   └── processed/     # Cleaned and transformed data
├── notebooks/         # Jupyter notebooks for analysis
├── src/              # Source code
│   ├── data/         # Data processing scripts
│   ├── features/     # Feature engineering scripts
│   ├── models/       # Model training scripts
│   └── visualization/# Visualization scripts
├── tests/            # Unit tests
├── docs/             # Documentation
├── requirements.txt  # Project dependencies
└── .gitignore       # Git ignore file

1. Create a virtual environment:

python -m venv venv
source venv/bin/activate  # On Windows: venv\Scripts\activate

2. Install dependencies:

pip install -r requirements.txt

Scrape 400+ reviews for each Ethiopian bank app from Google Play Store:

python src/data/scrape_reviews.py

• Output: data/raw/raw_reviews.csv

Clean the scraped reviews, remove duplicates, handle missing data, and normalize dates:

python src/data/clean_reviews.py

• Output: data/processed/cleaned_reviews.csv

Extract common themes and generate word clouds for each bank:

python src/features/theme_analysis.py

• Output: data/analysis/themes_by_bank.csv and word cloud images in data/analysis/

Explore and visualize the data:

cd notebooks
jupyter notebook

Open bank_reviews_analysis.ipynb for interactive analysis.

Run all tests to verify functionality:

pytest tests/

• Follow PEP 8 style guide
• Write tests for new features
• Update documentation as needed # Customer-Experience-Analytics-for-Fintech