Research
Here at SAGB, we create research proposals. We tackle problems from all sports and aim to use data to come to conclusions. These are the reports made in SAGB so far. We also consult with professional teams to solve real world problems.

Classification of NBA Salaries through Player Statistics
By William Wu, Kevin Feng, Raymond Li, Kunal Sengupta, Austin Cheng
This research creates a classification-based model that predicts the salary amounts given to NBA players in free agency. Correlation analysis demonstrated that points, turnovers, VORP, and rebounds created a balanced and effective set of variables for unweighted KNN-classification. After classification, the model revealed that volume statistics were most indicative of salaries within lower and mid-level players, while high VORP was common among all players making near-max to max salaries. The model was used to predict salaries for incoming free agents in the 2018 class, with reasonable projections that meet qualitative expectations. Read the full report here

Analysis of the Effects of Positional Features on NBA Shot Efficiency
By Rahul Bhatt, Rohan Suresh, Shloak Jain, Aditya Bollam, Lovish Murjal
This paper details how the team built a model that takes in player movement data from NBA games and uses it to predict shot makes and misses. The team used logistic regression to train the classifier based on a series of different movement features for each possession
Read the full report here

San Jose Earthquakes Concessions Pricing Strategy
By Kevin Wu, Nitin Manivasagan, Haoran Guo, Alex Heuer
This research analyzes the concession pricing for the San Jose Earthquakes, and gives recommendations as to how the pricing schemes can be better. The analysis includes how to best align the pricing such that the team profits from their concessions.
Read the full report here

Use of FAR to rate NFL teams
Developing a Metric to Evaluate the Performance of NFL Franchises in Free Agency
By Sampath Duddu, William Wu, Austin Macdonald, Rohan Konnur
This research creates and offers a new metric called Free Agency Rating (FAR) that evaluates and compares franchises in the National Football League (NFL). FAR is a measure of how good a franchise is at signing unrestricted free agents relative to their talent level in the offseason.
Read the full report here
Social Network Analysis of NBA teams
Relationships Between Fandoms in American Professional Sports: A Trial in Data Visualization and Art
By Derek Topper
This project explores the relationships between the fanbases of the 123 American professional sports teams through a network analysis of the shared followers between the Twitter accounts of each set of two teams. After a month of web-scraping, a database containing all of the follower identification numbers of each Major League Baseball, National Football League, National Basketball Association and National Hockey League team was created. Various visualizations were created in order to depict these relationships.
Read the full report here