Another weekend, another exciting hackathon. MachineHack is back with the 6th instalment of the popular weekend hackathon series, and this time we challenge data scientists to predict the grade of glass manufactured in MachineHack’s Glass Quality Prediction: Weekend Hackathon #6.

The challenge will start on May 22nd Friday at 6 pm IST.

Problem Statement & Description

We humans have been using glass since ancient times for a variety of applications from building construction to making decorative objects. With technology, glass and its applications have evolved, and today, we have different varieties of glass used for very different purposes from a computer monitor to a bulletproof car window depending on the grade of the glass produced. And not all grades or varieties are manufactured the same way. In this data science challenge, you as a data scientist must use the given data to predict the grade of the glass produced based on the given factors.

Given are 15 distinguishing factors that can provide insight into what grade of the glass is being produced. Your objective as a data scientist is to build a machine learning model that can predict the grade of glass based on the given factors.

Data Description

The unzipped folder will have the following files.

• Train.csv – 1358 observations.
• Test.csv – 583 observations.
• Sample Submission – Sample format for the submission.

Target Variable: class

The datasets will be made available for download on May 22nd, Friday at 6 pm IST

Below are the file formats for the provided data

Train.csv

Test.csv

Sample_Submission.xlsx

The submission must contain the probabilities of the target classes 1 and 2.

Bounties

The top 3 competitors will receive a cool AIM goodie bag and a free pass to the plugin.

plugin, India’s largest virtual conference on AI, is a next-gen disruptive conference that brings AI professionals from around the world together in a virtual setting.

Know more about the plugin here.

Rules

1. One account per participant. Submissions from multiple accounts will lead to disqualification
2. The submission limit for the hackathon is 10 per day after which the submission will not be evaluated
3. All registered participants are eligible to participate in the hackathon
4. This competition counts towards your overall ranking points
5. You will not be able to submit once you click the “Complete Hackathon” button. You may ignore this feature
6. We ask that you respect the spirit of the competition and do not cheat
7. This hackathon will expire on 25th May, Monday at 7 am IST

Evaluation

The leaderboard is evaluated using log_loss for the participant’s submission.