## Goal
The goal of this competition is to use the given data to predict the risk of an accident involving a recorded vehicle. (Note: The risk variable represents the owner of the dashcam, not necessarily the vehicle that will have an accident.)

## Metric
The evaluation metric for this competition is [**Roc Auc Score**](https://en.wikipedia.org/wiki/Receiver_operating_characteristic).

The ROC curve is the plot of the true positive rate (TPR) against the false positive rate (FPR) at each threshold setting. AUC means area under the curve of ROC.

TPR is the proportion of samples that are correctly judged as positive among all samples that are actually positive. FPR means the proportion of samples that were incorrectly judged as positive among all samples that were actually negative. These two rate are given by:

$$ \text{TPR} = \frac{\text{TP}}{\text{TP}+\text{FN}}\  ,\ \text{FPR} = \frac{\text{FP}}{\text{FP}+\text{TN}} $$

A receiver operating characteristic curve, or ROC curve, is a graphical plot that illustrates the performance of a binary classifier model (which can also be used for multi-class classification) at varying threshold values. ROC analysis provides tools to select potentially optimal models and discard suboptimal ones independently from, and prior to specifying, the cost context or class distribution. It is directly and naturally related to the cost/benefit analysis of diagnostic decision making.

## Submission Format

Please submit the file in .csv format that includes two features: `film name` and `risk`. You may refer to the dataset for a sample submission file.