March Data Crunch Madness - 2021 Overview

Slide Note

The 8th Annual March Data Crunch Madness event sponsored by Prof. Petersen from Fordham University involves predicting game outcomes in the March Madness Tournament. Teams compete for prizes, following strict competition rules and submission deadlines. Interdisciplinary teams are encouraged, and participants must demonstrate analytical skills using data from 2002 to 2020. Teams can create impactful visualizations and submit their predictions for the chance to win cash prizes.

benc_nah Follow

Uploaded on Oct 05, 2024 | 0 Views

Download Presentation

Please find below an Image/Link to download the presentation.

The content on the website is provided AS IS for your information and personal use only. It may not be sold, licensed, or shared on other websites without obtaining consent from the author. Download presentation by click this link. If you encounter any issues during the download, it is possible that the publisher has removed the file from their server.

E N D

Presentation Transcript

8thAnnual March Data Crunch Madness Overview - 2021 Sponsored By: Prof. Petersen, Fordham University 1

Timeline 02/01/21 Historical Data Released 02/08/21 Registration Deadline for Teams 11-59 PM 02/26/21 Initial Predictions CSV Submission due by 5 PM 03/15/21 2021 Current Season Data Released by 5PM 03/18/21 2021 Final Tournament Predictions CSV due by 1PM sharp 03/24/21 2021 Final PowerPoint Report & Participation Honor Code Declaration Form due by 11-59 PM 04/02/21 Final Poster Session & Awards Ceremony **all competition policies and procedures subject to strict compliance, and changes if any, by sponsor/organizer. Prof. Petersen, Fordham University 2

Competition Rules 1st Prize: $750 for team 2nd Prize $500 for team 3rd Prize $250 for team Team will split the money equally among the 4 team members. All team members are expected to contributed equally. All teams have to submit signed Participation Honor Code Declaration Form. Interdisciplinary teams across various programs are encouraged. The competition is open to all undergraduate and graduate students. All policies and procedures must be strictly complied with. No exceptions. Violations of policies and procedures will result in disqualification. Prof. Petersen, Fordham University 3

Where to Create Teams Please email team name and members (and copy all members) to: mdcm@fordham.edu Teams will then be added to the March Madness Blackboard 2021 organization. Create a team of 4 and upload the Excel file to blackboard via link by, 2/8/21, 11:59 pm. Designate one team member to upload. Materials will be uploaded there. Weekly coaching workshops will be held. In order to qualify for prize consideration a team of 4 must be intact and submit final report together (if team members drop midway, a team is disqualified). A team cannot drop/add members after 2/8/21. All team members must be present at virtual judging event A minimum of 10 teams are required for competition to continue to move forward into virtual judging event. Prof. Petersen, Fordham University 4

https://www.kaggle.com/c/mens-machine-learning-competition-2019https://www.kaggle.com/c/mens-machine-learning-competition-2019 https://www.kaggle.com/c/mens-machine-learning-competition-2019 https://www.kaggle.com/c/mens-machine-learning-competition-2019 Objective Based on Kaggle s Machine Learning Mania https://www.kaggle.com/c/mens-machine-learning-competition-2019 Predict the probability that a team wins any given game in the March Madness Tournament Predict all possible 2278 matches Use data from 2002 until 2020 to train and test until data for 2021 is released Be creative! See if you can find signal in the noise Demonstrate your analytical skills Visualize your findings Prof. Petersen, Fordham University 5

Dataset Overview Glossary available on Blackboard Game Data: game_id, host name and latitude and longitude and score KenPom Data: four factor data, tempo, efficiency, etc. Do not share outside of Fordham Coaching Data: Coach name, career wins, season wins, NCAA tournament appearances, Sweet 16 appearances, and Final 4 appearances Team Location Data: Latitude and longitude of team1 and team2 Team Data: Team Name Poll Data: AP Pre season/Final Polls, Coaches Preseason/Final Polls RPI Data Prof. Petersen, Fordham University 6

Grading Criterion Judges will grade the submissions on the following factors Model Accuracy How well did the model perform? Creativity of Exploratory Analysis & Methodology Was the team able to find novel ways to improve accuracy and gain new insights into what makes teams succeed in March? Communication & Visualization How well was the team able to effectively communicate their findings to the judges Extremely important to Deloitte!! Note: Model accuracy is not the most important. Very important to find creative ways to analyze the data and effectively communicate! Prof. Petersen, Fordham University 7

Format of Poster Board Overview & Introduction Hypothesis & Methodology Variable Selection, Analytics Explored, Data Mining Techniques Analytics & Results Results of Analytics, Results of Data Mining Techniques Conclusions & Suggestions for Improvement Performance of Model Prof. Petersen, Fordham University 8

Tutorials What is Log Loss? (Blackboard) SPSS Logistic Regression Example (Blackboard) Python Logistic Regression Example (Blackboard) Other examples (Right) Method Software Link Decision Trees R http://statsguys.wordpress.com/2014/03/ Python (NumPy) Iterative Strength Rating http://bit.ly/1vzPIJX Probability Distribution Excel http://bit.ly/1BvIadI Network Analysis STATA http://bit.ly/1GwgF2b Generalized Boosted Model (Decision Trees) R https://github.com/chmullig/marchmania Ordinal Logistic Regression and ExpectationR http://bit.ly/1As9dEr Various SAS http://bit.ly/1weYwQd Proprietary (Interesting Video Discussion) SAS http://www.unf.edu/~jcoleman/dance.htm Ensemble (Support Vector, Na ve Bayes, KNN, Decision Tree, Random Trees, Neural Nets) N/A http://bit.ly/1BvIskU Python (scikit-learn)http://bit.ly/1LINr2U Random Forest Prof. Petersen, Fordham University 9