Wharton Data Science Competition: Basketball Predictions 2025
21 Questions
0 Views

Choose a study mode

Play Quiz
Study Flashcards
Spaced Repetition
Chat to Lesson

Podcast

Play an AI-generated podcast conversation about this lesson

Questions and Answers

What platform is used to submit the work in Phase 1?

SurveyMonkey Apply (Apply) is the platform used for submissions in Phase 1.

What is the primary task in Phase 1a?

The primary task in Phase 1a is to rank the top 16 teams in three of the four regions (West, North, and South).

What are the top 5 teams expected to do in Phase 3?

The top 5 teams are invited to present their work from Phase 2 to a panel of judges during a virtual meeting.

What aspect of the competition involves creating a short slide deck?

<p>Creating a short slide deck describing the team's methods and findings from Phase 1 is a task in Phase 2.</p> Signup and view all the answers

What is the aim of this competition?

<p>The aim of this competition is to use data to predict the outcome of college basketball games and develop a strategy for the tournament.</p> Signup and view all the answers

What is the primary goal of this analysis, as outlined in the provided content?

<p>The primary goal is to predict the winning probabilities for 10 first-round games in the East Region, including a play-in game, using data-driven methods.</p> Signup and view all the answers

What key aspect of the analysis is emphasized beyond the seed number?

<p>The analysis emphasizes focusing on the statistics and strategies that truly matter, rather than just the seed number.</p> Signup and view all the answers

What is the expected format for submitting predictions for each game?

<p>Each game prediction should be a numeric probability between 0 and 1, representing the higher-seed team's &quot;chance to win.&quot;</p> Signup and view all the answers

Describe the intended audience for the methodology summary.

<p>The methodology summary is intended for a team comprised of head coaches and front office executives.</p> Signup and view all the answers

What are the two key aspects described in the "Your Predictions" section of the methodology summary?

<p>The &quot;Your Predictions&quot; section describes how team rankings were created and how game-winning probabilities were determined.</p> Signup and view all the answers

What is the purpose of the "Your Insights" section in the methodology summary?

<p>The &quot;Your Insights&quot; section addresses model performance assessment, use of generative AI tools, and any additional data sources.</p> Signup and view all the answers

What is the primary responsibility of the student team leader in the Wharton High School Data Science Competition?

<p>To submit the team’s Phase 1 answers in Apply.</p> Signup and view all the answers

What types of statistics are provided in the dataset for the basketball tournament analysis?

<p>Game-level and team-level stats including scores, field goals attempted (FGA), offensive rebounds (OREB), and turnovers (TOV).</p> Signup and view all the answers

Why should competitors avoid looking at the actual 2022 NCAA tournament results during their analysis?

<p>Because the actual results will not be helpful in creating independent rankings and hypothetical matchups.</p> Signup and view all the answers

What is the main objective of the teams participating in the basketball analytics competition?

<p>To analyze the previous season's data to rank teams and predict outcomes of hypothetical matchups.</p> Signup and view all the answers

In addition to accuracy, what aspect of methodology must teams clearly explain in the competition?

<p>Justification of their choices with sound reasoning.</p> Signup and view all the answers

How many games worth of statistics are teams required to analyze for their predictions?

<p>Over 5,300 games.</p> Signup and view all the answers

What format are the competition data files provided in?

<p>.csv files and Google Sheets.</p> Signup and view all the answers

How many rows are in the primary dataset for the NCAA regular season games?

<p>11,600 rows.</p> Signup and view all the answers

What is the purpose of the educational modules provided to the competition participants?

<p>To help participants understand key basketball terms and their relevance to the competition.</p> Signup and view all the answers

What is included in the tournament teams data?

<p>Teams with winning records eligible for the tournament.</p> Signup and view all the answers

Flashcards

Phase 1: Main Competition

The first phase where teams analyze stats and rank teams.

Predicting Winners

Using analysis to forecast which teams will win matchups.

Ranking Teams

Assigning ranks to teams based on their performance stats.

Winning Probabilities

Calculating the likelihood of a team winning their matches.

Signup and view all the flashcards

Home-Court Advantage

The benefits a team gets when playing on its own home ground.

Signup and view all the flashcards

Semifinals

The second phase for the top 25 teams to present their findings.

Signup and view all the flashcards

Slide Deck Creation

Making a visual presentation of methods and findings.

Signup and view all the flashcards

SurveyMonkey Apply

The online platform used for submitting competition entries.

Signup and view all the flashcards

Play-In Game

A preliminary matchup where teams compete for a chance to enter the main tournament.

Signup and view all the flashcards

Team Rankings

A system used to evaluate and order teams based on their performance metrics.

Signup and view all the flashcards

Data Cleaning

The process of correcting or removing erroneous data before analysis.

Signup and view all the flashcards

Statistical Methods

Techniques applied to analyze data and model outcomes.

Signup and view all the flashcards

Performance Assessment

Evaluating the accuracy and reliability of the predictive model used.

Signup and view all the flashcards

Key Drivers of Performance

Factors that significantly influence a team's success or failure in games.

Signup and view all the flashcards

Analytics Staff Role

The team responsible for analyzing game statistics to drive performance.

Signup and view all the flashcards

Generative AI Tools

Software that uses algorithms to generate content or data predictions.

Signup and view all the flashcards

Data Set

A collection of game-level and team-level statistics from the 2022 NCAA season.

Signup and view all the flashcards

Simulation

Creating hypothetical matchups to test predictions without actual outcomes.

Signup and view all the flashcards

Rethinking Strategies

The process of analyzing past performance to improve future outcomes.

Signup and view all the flashcards

Tournament Seeding

Ranking teams to determine matchups in a tournament structure.

Signup and view all the flashcards

Methodology

The approach used to analyze data and make predictions.

Signup and view all the flashcards

Communication

The ability to present findings clearly and effectively to an audience.

Signup and view all the flashcards

Accuracy in Predictions

How closely your predictions match the simulated game outcomes.

Signup and view all the flashcards

Competition Data Files

Data is provided through .csv files in a Box folder and Google Sheets.

Signup and view all the flashcards

Primary Dataset

Contains all games played in a season with team results and descriptors, n=5300 games, n=11,600 rows.

Signup and view all the flashcards

Tournament Teams

Teams with winning records that may compete in tournament regions.

Signup and view all the flashcards

Predictive Games

Data for predicting outcomes of games, with one row per game in the East Regional.

Signup and view all the flashcards

Educational Modules

Resources to learn basketball terms and data relevance in the competition.

Signup and view all the flashcards

Possessions

The concept of teams having opportunities to score during a game.

Signup and view all the flashcards

Probability Models

Logistic models used to calculate the probabilities of game outcomes.

Signup and view all the flashcards

Study Notes

Wharton High School Data Science Competition: Basketball Tournament Predictions - 2025 Workbook for Phase 1

  • The workbook is designed to help students develop their approach to analyze basketball data and predict tournament outcomes
  • Students are responsible for submitting their Phase 1 answers through the Apply platform
  • The competition tasks students to analyze over 5,300 basketball games from the 2022 NCAA Women's Division 1 season
  • Students need to rank teams within regions and predict the winners in hypothetical matchups
  • Data includes various game statistics like scores, field goals attempted, offensive rebounds, turnovers, etc.
  • The goal is to reimagine the season outcomes, considering hypothetical matchups
  • Students should create their own rankings and predict outcomes of matchups that did not actually happen
  • The participants will not use the results of the actual 2022 NCAA tournament in their analysis as it would not be helpful
  • Success depends on demonstrating accuracy, sound methodology, and clear communication skills through the analysis and presentation of results
  • The competition is divided into three phases: Phase 1 (main competition), Phase 2 (Semifinals), and Phase 3 (Finals)
  • Phase 1 involves analyzing over 5300 games to rank and predict winning teams in hypothetical matchups, submitted through an online platform.
  • Phase 2 consists of creating a presentation, detailing the teams’ methodology and findings and exploring home court advantage
  • Phase 3 involves a final presentation of the Phase 2 submission to a panel of judges.
  • A bracket displays competition tasks for three regions, including winning probabilities for one region and rankings within other regions
  • The data sources are provided as .csv files, Google Sheets, in an online folder
  • The primary dataset includes descriptions of game outcomes for each game and team
  • The competition has educational resources, including several videos to explain the competition and its terminology

Studying That Suits You

Use AI to generate personalized quizzes and flashcards to suit your learning preferences.

Quiz Team

Related Documents

2025 Wharton High School Data Science Competition Workbook PDF

Description

This workbook helps students analyze basketball data to predict tournament outcomes for the NCAA Women's Division 1 season. Participants will rank teams and forecast winners in hypothetical matchups using various game statistics. Success in this competition relies on innovative analysis and imaginative matchup scenarios.

More Like This

Moneyball: The Art of Winning Quiz
24 questions

Moneyball: The Art of Winning Quiz

Dhruv123 avatar
Dhruv123
Regression Analysis of Baseball Stats
32 questions

Regression Analysis of Baseball Stats

TruthfulRealism2101 avatar
TruthfulRealism2101
Baseball Data Analysis with R and Python
32 questions

Baseball Data Analysis with R and Python

TruthfulRealism2101 avatar
TruthfulRealism2101
Run Expectancy and Value Calculation
29 questions

Run Expectancy and Value Calculation

TruthfulRealism2101 avatar
TruthfulRealism2101
Use Quizgecko on...
Browser
Open
Browser
Browser