Porto Seguro Safe's Driver Prediction

Describe project

Nothing ruins the thrill of buying a brand new car more quickly than seeing your new insurance bill. The sting’s even more painful when you know you’re a good driver. It doesn’t seem fair that you have to pay so much if you’ve been cautious on the road for years.

Porto Seguro, one of Brazil’s largest auto and homeowner insurance companies, completely agrees. Inaccuracies in car insurance company’s claim predictions raise the cost of insurance for good drivers and reduce the price for bad ones.

In this competition, you’re challenged to build a model that predicts the probability that a driver will initiate an auto insurance claim in the next year. While Porto Seguro has used machine learning for the past 20 years, they’re looking to Kaggle’s machine learning community to explore new, more powerful methods. A more accurate prediction will allow them to further tailor their prices, and hopefully make auto insurance coverage more accessible to more drivers.

Objective

The objective is use supervised learning technical for understend how severe is an insurance claim.

Documentation

The documentation: https://www.kaggle.com/c/porto-seguro-safe-driver-prediction

Datasource

The datasource: https://www.kaggle.com/c/porto-seguro-safe-driver-prediction

Algoritms

Random Forest
XGBoost

Quickstart

Data Exploration and Modeling

Struture this Project

.
├── data
│   ├── kaggle_submission.csv
│   └── raw
│       ├── datasets.zip
│       ├── sample_submission.csv
│       ├── test.csv
│       └── train.csv
├── LICENSE
├── notebooks
│   └── porto_seguro_safe_driver.ipynb
├── README.md
├── references
│   └── porto-seguro-vector-logo.png
└── src
    └── environment
        ├── config_environment.txt
        ├── container
        │   └── Dockerfile
        ├── create_requirements.sh
        ├── create_virtual_env.sh
        ├── __init__.py
        ├── jupyter_notebook_config.py
        ├── makefile
        ├── prepare_env.py
        ├── README.md
        ├── requirements.txt
        ├── show_config_environment.sh
        ├── show_struture_project.sh
        ├── struture_project.txt
        ├── test_environment.py
        ├── venv
        └── virtualenv_requirements.txt

8 directories, 24 files

Requirements

Python 3.7.3 or more

sudo apt-get install Python3.7.3

sudo apt-get install python3-pip

Python Virtual Environment

pip3 install --user virtualenv==16.6.0

sudo apt-get install git

Running

Clone this repository

git clone https://github.com/brunocampos01/challenge-keyrus
cd challenge-keyrus

Choose which environment to running

In terminal running command jupyter-notebook and navigate in this repository: notebooks

NOTES

All the development was done using virtualenv.
To learn more about the environment that has been developed, access the file config_environment.txt

Author

Bruno Aurélio Rôzza de Moura Campos (brunocampos01@gmail.com)

Copyright

This work by Bruno A. R. M. Campos is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.

yesjuhyeong/porto-seguro-safe-driver-prediction