Many enthusiasts and experts publish forecasts of the order players are drafted into professional sports leagues, known as mock drafts. Using a novel dataset of mock drafts for the National Basketball Association (NBA), we analyze authors' mock draft accuracy over time and ask how we can reasonably use information from multiple authors. To measure how accurate mock drafts are, we assume that both mock drafts and the actual draft are ranked lists, and we propose that rank-biased distance (RBD) of Webber et al. (2010) is the appropriate error metric for mock draft accuracy. This is because RBD allows mock drafts to have a different length than the actual draft, accounts for players not appearing in both lists, and weights errors early in the draft more than errors later on. We validate that mock drafts, as expected, improve in accuracy over the course of a season, and that accuracy of the mock drafts produced right before their drafts is fairly stable across seasons. To be able to combine information from multiple mock drafts into a single consensus mock draft, we also propose a ranked-list combination method based on the ideas of ranked-choice voting. We show that our method provides improved forecasts over the standard Borda count combination method used for most similar analyses in sports, and that either combination method provides a more accurate forecast over time than any single author.
翻译:暂无翻译