# This round is being scrapped for a while due to upload of wrong dataset. Please bear with us while we  update the dataset.
Welcome to CODEMARATHON 5.0 - MACHINE LEARNING (Round 2) which is being organized by CSES, Dept. of Computer Science and Engineering, IIT (ISM), Dhanbad.
## Problem Statement
Congratulations on performing well in Round 1 of this competition. It's time that we give your heavy-duty hardware, that that can grind through all those images like a beast, some well-deserved rest with a small and easy (or is it?!) CSV based dataset.

This round is a **weird** one. The challenge is to **generalize to a test set of 20000 samples** using only a handful of training examples **(300,  to be precise)**. All you have to do is model your predictions on a 20,000x300 matrix of test samples using only 300 training samples... **without overfitting**!

Your task is to predict a binary target variable based on 300 features.

Do your best, model without overfitting and win! Your data science-y insights might help you with this one.

People overfit like crazy, can you not?

## Data
The train set contains 300 samples, each consisting of an identifier (indexes into the data), 300 features (based on which you have to predict the binary target) and the target itself (true binary label for the sample).

You have been provided with the relevant dataset for this competition in a zip file 'data.zip'. Please see the [data section][1]  for downloading the data. The dataset and submission formats have been described in detail in the data tab/section.

## Competition Rules 
Please have a look at the competition rules [here][2]. All rules are to be followed strictly. Any use of unfair means will result in immediate disqualification from the competition.

## Competition Timeline
Start: 8:00 pm, 19th March 2019
End: 11:59 pm, 31st March 2019

## Submisssion Deadline
11:59 pm, 31st March 2019

## Evaluation
For information related to evaluation, please see the [evaluation  section][3] (on the left).


  [1]: https://www.kaggle.com/c/code-marathon-ml-2/data
  [2]: https://www.kaggle.com/c/code-marathon-ml-2/rules
  [3]: https://www.kaggle.com/c/code-marathon-ml-2#evaluation