March Madness Series - Fab Four

Through a series of four challenges, you will build a tool that gathers information on teams and players by analyzing textual material from top sports writers and commentators- the material  could include game reports, columns, Twitter feed, blogs.  The tool should be able to help categorize players based on their skills, temperament, role/position etc, from these materials, using the capabilities of IBM Watson. 

You can see the first challenge here: https://www.topcoder.com/challenges/30063503/
And the second challenge here: https://www.topcoder.com/challenges/30063887

Description

In this third challenge, you are looking to form a Dream Team of 5 players, selected from the Final Four teams. The Dream Team is not merely about the combination of right skills, but also of personalities that can work well together.  For insights into personality,  you should combine their scores on the ‘Big Five’ personality characteristics with comments from experts.  For example: if all the players are low on ‘agreeableness’, then the team may not work together as a unit. If a player has a high score on ‘anger’, then there is a risk of him being fouled out. 

The task in this challenge is to identify the personality of the players, their roles and skills and suggest the dream team(s). You could get the ‘Big Five’ scores of the players through their twitter feeds - look at this example provided by IBM for ideas. 
https://personality-insights-demo.ng.bluemix.net/

However, the players might display different personalities on and off the court; and Twitter personality scores may be off the mark.  So you should cross-reference your recommendations with experts’ comments through their news reports, blogs etc. 

Your system should allow the user to enter:

• The number of players in any of these  positions -  guard, forward and center. 
• The number of players for each Big 5 personality characteristic (Agreeableness, Conscientiousness, Extraversion, Emotional Range, Openness) and values High, Low. 
• The condition to specify the number of players should include ‘at least’, ‘at most’  and ‘equal to’  values. 
• The validation for the total number of players across all positions should be 5. 
• The validation for the total number of players across all personality characteristics should be 3. (The team has five members based on required position; however only up to three players can be picked based on personality requirements too.)

If the Personality Score based on Twitter is in contradiction with an expert opinion, then the expert opinion could be the deciding factor. For example, irrespective of what his Twitter Personality is, Myron Medcalf of ESPN rates Udoka Azubuike high on Emotional range. 
http://www.espn.in/mens-college-basketball/story/_/id/22914235/why-michigan-loyola-chicago-villanova-kansas-win-national-championship-2018-final-four

The interface should allow the user to make a selection like this:

• Select a team with at least 3 guards and at most two players with low “agreeableness” scores
• Select a team with 2  guards, 1 center and 2 forwards, with at most 1 player with High Emotional Range and at least 2 with High Agreeableness.

Even though the user is not specifying  skills like 3-point shooting, rebounding etc your results will be rated higher if these skills are mentioned in the team listing.

You could look at  sites like  NCAA, Yahoo sports, ESPN, Sporting news etc for reports on the game. 
For the sake of uniformity across participants, the teams are from the men’s tournament - no discrimination intended.  

Requirements

1. Please join the Topcoder Cognitive Community if you have not already, and get an IBM Cloud Account by using this link.
2. You can give as many team compositions as you can. Each set  should contain the player names, player team, Big 5 personality scores , skills and expert comments. (commentator name, publication, url of the comments/news item, a short extract from the comments.)
3. User interface that allows entry of values for both player position and Big 5 personality traits as described above.
4. A design document on your approach.

Final Submission Guidelines

1. Deploy your application to your own IBM Cloud instance.
2. Upload a .zip containing your source code and a text file called ibm-cloud-deployment.txt.  This .txt file should contain the URL defined above for us to test.
3. You can use any programming language to build the application, as long it’s supported by IBM Cloud, has an api, provides a UI, and meets the spec criteria.
4. Detailed instructions on deploying and testing it locally

Review Guidelines

1. Richness of Model

• Does the model utilize and exploit NLU and Personality Insights features?
• Richness of model will not score any points  if there is no implementation. However, the implementation could be for a section of the model.  

2. Implementation

• IBM Discovery/NLU/Personality Insights features used to demonstrate the solution
• Design and code quality

3. Documentation

• A document explaining your solution.  How are you enhancing the output?
• A demo video of your solution

4. Ease of Use

• How easy it is to set up and test the solution
• User Interface - Functional interface should be sufficient to get a pass score.

5. Performance on new/unknown data

• How well does the solution perform against user queries?