by Chin-yu Wu, School of Informatics graduate student

As a spectator watching a basketball game, I always want to know how close my team is to winning the game when the team is having the lead. On the other hand, when the team is trailing I want to know the probability of coming back under this situation, or even in a game that is not that close I always wonder whether the game will come down to the wire or not. These numbers and information sometimes could be estimated by some experienced fan’s intuition, but for a spectator that does not have that much experience watching the game would see this information very valuable.

The main product of this project is a dashboard that could let the users interact. The dashboard could let the users choose the margin of points and time left on the play clock (20:00, 16:00, 12:00, 8:00, 4:00), then the probability of winning and the game becoming a close game would come out. The reason I choose these time periods is because these are the college media timeouts. In this research, the definition of a close game is under 4 minutes and the margin of points is within four. The probability of the game winning by the home team is based on logistic regression and the probability of it becoming a close game is based on a 3-layer neural network. The data I used is all the conference games from the 2023-2024, 2022-2023, and 2021-2022 seasons. The reason I only used conference games is because these games are more evenly matched. It will have fewer games that are won by 20 or more points.  so the result of the model is more valuable and accurate.

(more…)

by Will Emhardt, School of Informatics graduate student

The dataset I decided to use for this project was the previous season of Division 1 Soccer, ending in December of 2023. Using college soccer data, I only pulled the list of contests for the 2023 season and then the play-by-play for every contest in 2023. Initially I set out to create a heatmap displaying all goals and shots with filters like time in the game, location on the field, and many more. As I dug into this objective I garnered curiosity to explore more realms within the soccer game.

First, I created the heatmap on a soccer pitch to show high and low density areas for shots and goals, then I decided I should have an option to show the same data as a scatterplot. Second, I created a set piece metric to show the attacking capability of teams off of set pieces and when defending set pieces. Third, I created a corner kick metric to also show the propensity to score immediately after a corner kick, or on the other side the capability of defending a corner kick. Lastly, I included a more general scatterplot with the ability to track individual athlete’s statistics. The general idea of the individual performance scatterplot was to display the certain strengths of players throughout Division 1.

All of these visuals and metrics are hosted on a Streamlit app where the user can filter the data however they please.

(more…)