TC - Machine Learning for Challenges Ideation Challenge

Challenge overview

Thanks to the amazing work from the community, Topcoder has been running over 52k challenges over the past few years.

In this challenge, Topcoder is reaching out to our creative Topcoder community to find ideas which will help with Topcoder challenge management and challenge success rates.

CHALLENGE BACKGROUND

Thanks to the amazing work from the community, Topcoder has been running over 52k challenges over the past few years.

Topcoder is reaching out to our creative Topcoder community to

• Research on the historical challenge data
• Build ML workflow using AWS Sagemaker
• Use ML technology to help with
  • Easy Topcoder challenge management
  • Increase challenge success rates. Challenge success here means one challenge gets one successful submission (winner) in the end.

Task Detail

Some data of past challenges is provided in the forum, which includes metadata for a challenge. We are open to any ideas which leverage machine learning, deep learning and the data shared. These ideas should help Topcoder team to have better challenge management or challenge success rates.

Here are two examples:

1. Give advice to copilot about the prize of the new challenge by analyzing its specification.
2. Before sending out to the community, if we are able to predict that one challenge would not get any submission, its copilot could do a lot, such as to modify challenge scope and to increase prize etc, to attract everyone to join the competition and make the challenge successful.

Please be creative, but also be realistic. If any data is needed but not included in current data, please ask in the forum and mention it in your report. In the first example idea, actually it requires challenge specification, which is not in current data.

Data Description

Please find csv data attached in the forum. The csv headers should explain it very well.

JUDGING CRITERIA and SCORECARD REVIEW

• This submission will use the Idea Generation scorecard.
• Your submission will be reviewed on these requirements:
  • Completeness of the idea
  • Feasibility of the idea
  • How much benefit it can provide to Topcoder platform
  • Number of ideas given

The winner will be chosen by the most logical and convincing reasoning as to how and why the idea presented will meet the objective. Note that, this contest will be judged subjectively by Topcoder. However, the judging criteria will largely be the basis for the judgement.

SUBMISSION FORMAT GUIDE FOR THE WHITE PAPER:

Your submission should include a text, .doc, PPT or PDF document that includes the following sections and descriptions:

• Overview: describe your approach in “laymen’s terms”
• Materials: did your approach use a specific technology? Any libraries? List all tools and libraries you considered part of your proposal
• Discussion: Explain what you attempted, considered or reviewed that worked, and especially those that didn’t work or that you rejected. For any that didn’t work, or were rejected, briefly include your explanation for the reasons (e.g. such-and-such needs more data than we have). If you are pointing to somebody else’s work (eg you’re citing a well known implementation or literature), describe in detail how that work relates to this work, and what would have to be modified
• Data: what about the data provided - is it enough to achieve your idea ? If not, what could be achieved and Why ? Any Correlations in the data that may not be immediately obvious
• Feasibility: GIven the data and approach you implemented, How feasible and realistic it is and Why ? What level of prediction accuracy can be obtained using this approach and justification for the same ?
• Assumptions and Risks: what are the main risks of this approach, and what are the assumptions you/the model is/are making? What are the pitfalls of the data set and approach?
• Other: Discuss any other issues or attributes that don’t fit neatly above that you’d also like to include

Final Submission Guidelines

see above