# Team Names
Make sure to enroll with the same team names that you submitted in NESS registration!

# Scoring 
The evaluation metric for the competition is the *Area Under the Receiver Characteristic Operating Curve* (AUROC). Let TPR denote the True Positive Rate, and x denote the False Positive Rate for a classifier. Note that TPR is a function of x.
Then AUROC (A) is defined as $$ A : = \int_{0}^{1} TPR(x) dx . $$
Thus, AUROC is a cumulative measure of a classifiers ability to detect true positives as we vary the type I error rate (i.e., False Positive Rate). The closer the AUROC is to 1, the better is your classifier. Your goal is to maximize AUROC. 

The AUROC metric can be computed in both python in R using the roc-auc-score function in sklearn.metrics. and the auc function in pROC, respectively.

# Submission Format 
 For policies indicated in the train/test split as test, submission files should have two columns - policy_id and conv_prob, which denotes the Policy ID, and the estimated probability of conversion.
Note, that the **conv_prob is a probability (i.e. between 0 and 1), and not a predicted class label**.

The CSV file should look like:

| policy_id  | conv_prob  |
| --- | --- |
| policy_5 | .2456  |
| policy_34 | .8976 |
etc. 

## Presentations:

The top teams will be invited to give a presentation to explain their models and findings to a panel of judges and Travelers employees and winners will be selected at NESS. Some questions to consider in your presentation are:

* What methods did you consider (you don’t have to actually try all the methods you considered; just ones that you think would work for this problem)?
* What method did you choose in the end, and why?
* How did you do your variable selection and feature engineering?
* What other variables not in the data set do you think might be useful?
* How could your model predictions be used in practice?
* Any interesting methods / findings, that can go unnoticed?