Please note that your overall score for Challenge Problem 1 will be based on both [Challenge 1.1](https://www.kaggle.com/c/application-failure-prediction-part1/overview) and [Challenge 1.2](https://www.kaggle.com/c/application-failure-prediction-part2/overview).

There are two evaluation components for this challenge. 

## Automated evaluation

For **automated evaluation**, we use balanced accuracy as the evaluation metric for your model. This will be based on the output of `model_complete_test.csv`. The **[balanced accuracy](https://www.kaggle.com/c/application-failure-prediction-part1/overview/definitions)** is computed by assigning equal weight to the positive and the negative class accuracy. Challenge participants are expected to achieve a minimum balanced accuracy of 60%, however, the winning teams will likely have an accuracy of 80% or higher.

## Offline evaluation

We will also evaluate selected teams based on their final reports and their presentations. This process is offline and may not be reflected on the competition leaderboard immediately. For details please see: https://syp.computer.org/gsc/

## Submission format

- Your code should generate the output file `model_complete_test.csv`This will be used for automated evaluation in Kaggle for Challenge 1.1.
- The output files must have two columns: 
      - `job_id`: Unique ID for the job.
      - `failed`: Based on the resource usage metrics, can you predict if the job will fail? A value of `1` indicates failure.
- You must also submit a report explaining the following:
      a. What did you do for the _Model Complete_? Give the confusion matrix and the balanced accuracy that you obtained on the training data.
- Upload your Python code with a README that tells us how we can run your code.