Skip to content

caetano-dev/PixFraudDetection

Repository files navigation

PIX Fraud Detector

Quick Start

Setup

# Create and activate virtual environment
python3 -m venv venv
source venv/bin/activate  # On Unix/macOS
# or: source venv/bin/activate.fish  # For fish shell
# or: venv\Scripts\activate  # On Windows

# Install dependencies
pip install -r requirements.txt

# Install duckdb

curl https://install.duckdb.org | sh

Data Preparation

Put the source AMLworld csv and text files in their data directories. Rename them to transactions.csv and accounts.csv as needed.

Running the Pipeline

python3 scripts/00_generate_convertion_rates.py
python3 scripts/01_filter_raw_data.py --dataset HI_Small # or HI_Large, LI_Small, LI_Large
python3 -m scripts.02_run_aggregation
python3 -m scripts.03_extract_features
python3 -m scripts.04_train_model_forward_chaining
python3 -m scripts.05_ablation_study
python3 -m scripts.07_summary

About

No description, website, or topics provided.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

 
 
 

Contributors

Languages