Features selection in NBA outcome prediction through Deep Learning
This work addresses outcome prediction for NBA basketball matches, but it is incremental as it compares existing features rather than introducing new methods.
The paper tackled NBA match outcome prediction by showing that models using a single feature (Elo rating or relative victory frequency) achieve better fit than those using box-score predictors like the Four Factors, with results based on data from 16 NBA regular seasons.
This manuscript is focused on features' definition for the outcome prediction of matches of NBA basketball championship. It is shown how models based on one a single feature (Elo rating or the relative victory frequency) have a quality of fit better than models using box-score predictors (e.g. the Four Factors). Features have been ex ante calculated for a dataset containing data of 16 NBA regular seasons, paying particular attention to home court factor. Models have been produced via Deep Learning, using cross validation.