NBA Expected Possession Value Demo - Shiny Contest Submission

NBA Expected Possession Value App

Authors: Jose Fernandez

Abstract: An app to visualize and interact with expected possession value (EPV) in the NBA. Highlights the use of interactive tables to display rich information. Resembles the concept of a traditional stock trading app in the context of sport.

Full Description: Expected possession value (EPV) is a framework for using optical player tracking data to estimate, in real time, the expected number of points obtained by the end of a possession in Basketball (Cervone et al, 2016).

This dashboard provides information at a play by play level for a full game as well as each player's total EPV added for that game. Users can interact with the main table various ways:

  • Filter the table by team
  • Hover over the sparkline to visualize changes in EPV within a play.
  • Open a dynamic plot to visualize the movement of the players and the change in EPV within a play

For more information about EPV and the data used in this app:
Cervone, D., D’Amour, A., Bornn, L., & Goldsberry, K. (2016). A multiresolution stochastic process model for predicting basketball possession outcomes. Journal of the American Statistical Association , 111 (514), 585-599. link | data


Keywords: NBA, sports, dynamic table, sparkline, reactable, DT, sport analytics
Shiny app: https://josedv.shinyapps.io/EPV_NBA_Dashboard/
Repo: GitHub - josedv82/EPV_NBA_Dashboard: A conceptual dashboard to visualize Expected Possession Value (EPV) in the NBA.
RStudio Cloud:

Thumbnail:
zplay_34

Full image: