This repository contains a series of Jupyter notebooks that form the basis of a data science project focused on fraud detection. The project is structured into three main components: data analysis, data forecasting, and data modeling.

This notebook is dedicated to the initial exploration and analysis of the dataset. It includes:

• Data cleaning and preprocessing
• Exploratory data analysis (EDA)
• Feature engineering
• Initial insights and observations

The final notebook is dedicated to building and evaluating machine learning models for predicting bank reserve levels. It includes:

• Splitting the dataset into training and testing sets
• Model selection and training (e.g., Linear Regression, Random Forest, XGBoost)
• Hyperparameter tuning
• Model evaluation and comparison

In this notebook, we focus on make predictions on new transactional data. It covers:

• Forecasting and evaluation

To run these notebooks, you will need to install the required Python packages. You can do this by running:

pip install -r requirements.txt

To use these notebooks, simply clone this repository and open the notebooks in Jupyter Lab or Jupyter Notebook:

git clone https://github.com/maikpaixao/banking_fraud_analysis.git
cd banking_fraud_analysis

Contributions to this project are welcome! Please feel free to submit issues or pull requests.

This project is licensed under the MIT License - see the LICENSE file for details.