Fun IBM Watson - Challenge Specs Classifier

Have you heard about the IBM Watson challenge series we organized for St. Valentine Day? Are you interested in Cognitive software solutions but not sure how to start because it looks complex? You are in the right place! Alongside the prized IBM Watson challenges this February, we will organize a series of smaller and easier challenges that will introduce you to different services provided by Watson. There is no a better way to learn a new technology than to try this technology on a simple but real problem!

If you don't have IBM Cloud Account yet, please register it via this link; also consider to join the renovated Topcoder Cognitive Community, if you have not already.

To make participation in these educational challenges even a bit more interesting, we offer some prizes:

• $1000 will be given to the member who has completed the most of these educational challenges (six in total). In case there are few such members, this prizes will be equality divided among them;
• Additionally, ten prizes, $200 each, will be randomly distributed among all members who have completed any of these educational challenges. During this random draw, your chance to get a prize will be proportional to the number of challenges you have completed, e.g. if we draw between just three competitors who have completed 1, 2, and 3 challenges each, their chances to be drawn will be: 16.7%, 33.0%, 50.0%.

In this challenge we want you to use Watson’s Natural Language Classifier service to train a text classifier able to distinguish between different tracks and sub-tracks of Topcoder challenges based on their specs.

To get challenges from TC API v3 use the following endpoints:

1. GET https://api.topcoder.com/v3/challenges
2. GET https://api.topcoder.com/v3/challenges/{CHALLENGE_ID} 

The endpoint (1) allows to pull down the list of active (if you append it with ?filter=status=ACTIVE) or past (if you append it with ?filter=status=COMPLETED) challenges. The endpoint returns at most 50 challenges in a single call, you can use offset=XXX query parameter for the pagination. The endpoint (2) allows you to get details for a specified challenge, including its specs.

For the purpose of this challenge you can create just a simple NodeJS script(s) that take any necessary intput parameters via command-line arguments, and, once the classifier is prepared, allow to pass in another specified challenge and return the track / subtrack determined for it.

Final Submission Guidelines

Submit your solution, including instructions on how to train the classifier and use it, along with a brief verification video, demonstrating it in action.