Towards a new meaning of modern basketball players positions
Basketball is one of the sports in which statistical analysis is most applied, thanks to the huge
amount of data that can be derived from any single game and statistical analysis is becoming more and more
important for many professional teams.
This work of thesis starts from the collaboration with MYAgonism, a Pavia startup which works
for providing advanced analytic tools to any basketball coach at any level in an affordable way.
The goal of the thesis is to find a new way to define positions of basketball players.
Three main technologies have been used in this work of thesis :
Self-Organizing Maps (SOM)
Multi-Dimensional Scaling (MDS)
Principal Component Analysis (PCA)
The whole software application was written in Python language.
Some external libraries have been integrated to provide the implementation of the described technologies, SOM, PCA and MDS.
PyMVPA implementation of SOM was used to perform the SOM algorithm.
The main module, called BasketballSOM, contains the main function that performs the whole SOM algorithm.
External modules have been implemented for the creation of the training set and the input set, and also for the visualization of results.
Training Set Characterization
The training set is the subset of the input space used to train the SOM and the topological characteristics of the output layer will
reflect the topological features of the training set. A criteria used to create a proper training set was including the 8 players with
the highest value of average minutes played per game from each of the 30 teams of the NBA.
Training the SOM with a training set made by just five elements, one for each classic basketball position: PG, SG, SF, PF, C.
The output layer of the SOM is divided in 5 clusters, one for each position.
Some Atypical players have been mapped on this output layer to show how classic positions are not able to describe their way of playing anymore.
Mapped players are LeBron James (LBJ23), Kawhi Leonard (KL2), Draymond Green (DG23) and Russell Westbrook (RW0).
The defined positions are satisfying in terms of description of players game.
A more detailed analysis can be performed, considering more sophisticated statistical categories to see if better positions definition can be performed.
The analysis should be extended to different leagues around the world, considering also non-professional players.
A proper selection of the statistical categories used to describe players and of the criteria to create training sets should be done on each different league.
Hopefully, the application will be integrated in the MYAgonism environment to provide a new tool for coaches around the world to be able to make the best decisions
for the performances and the results of their team.