Jyoti Nigania

Hi,i am writing blogs for our platform House of Bots on Artificial Intelligence, Machine Learning, Chatbots, Automation etc after completing my MBA degree. ...

Full Bio 

Hi,i am writing blogs for our platform House of Bots on Artificial Intelligence, Machine Learning, Chatbots, Automation etc after completing my MBA degree.

A Strong Determination Of Machine Learning In 2K19
15 days ago

Data Science: A Team Spirit
22 days ago

If You Are A Beginner Then Have Handy These Machine Learning Books To Gain Knowledge
23 days ago

Industry Automation Is Gearing Up Various Companies
25 days ago

Perks Of Becoming A Big Data Engineer Highlighted In A YouTube Video
31 days ago

These Computer Science Certifications Really Pay Good To You

List Of Top 5 Programming Skills Which Makes The Programmer Different From Others?

Which Programming Language Should We Use On A Regular Basis?

Cloud Engineers Are In Demand And What Programming Language They Should Learn?

Python Opens The Door For Computer Programming

Google and NCAA Host A.I. Bracket Competitions Via Kaggle

By Jyoti Nigania |Email | Mar 9, 2018 | 8172 Views

Google's Kaggle platform will be playing host to a Google and NCAA co-sponsored competition centering around the college basketball tournament formally known as March Madness. Basically who are not aware, Kaggle is a dedicated platform for sharing data sciences and machine learning expertise, parallel learning about the topic and competing for prizes. In this case, teams who register through the Kaggle site will be making use of historical NCAA data and creating algorithms that will be used by A.I. to fill a bracket. The set goal will be to create algorithms that can, in the second stage of the contest, accurately predict the outcome of 2018 NCAA Division I Men's and Women's Basketball Championships. To in roll for the competition, the sponsoring companies have to put up $100,000, split between the Men's and Women's divisions. That means that in either or both divisions, competing teams can take home $25,000 for first prize, $15,000 for second place, or $10,000 for third. 

Stages for the two concurrent competition is split into two stages:

  • The first stage centers around the creation of accurate A.I. algorithms.
  • The second stage centers around the upcoming NCAA games. 

The latter is the only portion that will count towards Kaggle-specific rankings or points. An equal number of points is available per game and points will be awarded or docked with secondary consideration given to the confidence in a prediction. A log loss function will be used in scoring, with a smaller log loss representing a better score. Those will work the same for both the Men's and Women's division of the championships but the competition dates will be slightly different for each one.

Stage 1 for the men's side starts on March 10. That will be followed by Stage 2 over the next two days and then from March 15 through the end of the associated basketball games. The final deadline for predictions on the men's side of the competition falls on March 15 at 3:00 pm UTC. The schedule for the competition pertaining to women's games follows a similar flow but beginning a day later. That means the stage 1 and the first part of stage 2 will fall on March 11 through March 13.  Meanwhile, the deadline for predictions on that front is March 16 at 3:00 pm UTC and the competition will end with the end of the tournament which begins on that same day.

Source: HOB