Predicting the winning team in basketball : a complex systems approach
| dc.contributor | Ph.D. Program in Management Information Systems. | |
| dc.contributor.advisor | Onay Şahin, Ceylan. | |
| dc.contributor.author | Ösken, Latif Cem. | |
| dc.date.accessioned | 2025-04-14T16:39:29Z | |
| dc.date.available | 2025-04-14T16:39:29Z | |
| dc.date.issued | 2023 | |
| dc.description.abstract | Predicting the winner of a basketball game is a difficult task, due to the inherent complexity of team sports. All 10 players on the court interact with each other and this intricate web of relationships makes the prediction task difficult, especially if the prediction model aims to account for how different players amplify or inhibit other players. Building our approach on complex systems and prototype heuristics, we identify player types through clustering and use cluster memberships to train prediction models. We achieve a prediction accuracy of ~76% over a period of five NBA seasons and a prediction accuracy of ~71% over a season not used for model training. Our best models outperform human experts on prediction accuracy. Our research contributes to the literature by showing that player stereotypes extracted from individual statistics are a valid approach to predict game winners. | |
| dc.format.pages | x, 146 leaves | |
| dc.identifier.other | Ph.D. Program in Management Information Systems. TKL 2023 U68 PhD (Thes TR 2023 L43 | |
| dc.identifier.uri | https://digitalarchive.library.bogazici.edu.tr/handle/123456789/21810 | |
| dc.publisher | Thesis (Ph.D.) - Bogazici University. Institute for Graduate Studies in the Social Sciences, 2023. | |
| dc.subject.lcsh | Basketball. | |
| dc.subject.lcsh | Team sports. | |
| dc.subject.lcsh | Prediction (Logic) | |
| dc.title | Predicting the winning team in basketball : a complex systems approach |
Files
Original bundle
1 - 1 of 1