Final Project - Financial Service

Data Wizard - Kelompok1A

All information related to the MSIB batch 5 data science final assignment at Rakamin Academy
Kick Off Final Project >>

Table of Contents

1. Introduction
2. Feature
3. Installation
4. Contributing
5. Roadmap
6. Note

Introduction

This project is a group project called Data Wizard which focuses on the topic of financial service. This project aims to build a machine learning model that can predict whether someone will be at risk of loan default or not. This model will be built using a dataset sourced from Kaggle.

Feature

The project performs various features, such as:

1. Data Collection: We acquire financial data from Kaggle, which serves as the foundation for our machine learning model.
2. Data Understanding: we carry out Exploratory Data Analysis, and create business insights
3. Data Preprocessing: We clean, transform, and prepare the dataset for model training.
4. Machine Learning Model: We build, train, and optimize a predictive model that evaluates loan default risk.
5. Evaluation: We assess the model's performance using relevant metrics like accuracy, precision, and recall.
6. Documentation: This readme serves as part of our documentation, providing an overview of the project.

Installation

To get started with our project, follow these installation steps:

1. Clone the project repository from our GitHub repository:

bash git clone https://github.com/HafiizhTH/FinalProject_Kelompok1A.git

2. To access the dataset we used, please click here.

Contributing

We welcome contributions from the community. If you want to get involved in our project, follow these steps:

1. Fork the project repository on GitHub.
2. Create a new branch for your contribution.
3. Make changes or additions to the project.
4. Commit your changes and create a pull request.
5. Our team will review your contributions and provide feedback.

Roadmap

Our project has several development steps planned. Some steps in the project roadmap include:

1. Extracting additional insights from data through deeper visualization and analysis.
2. Model customization and prediction performance improvement.
3. Integration with additional data sources to increase prediction accuracy.

Note