MODERN BASKETBOLDA HÜCUM VERİMLİLİĞİNİN OYUN TÜRLERİNE DAYALI DİNAMİKLERİ

Öz

NBA’de hücum stratejileri, analitik modellemelerin gelişimiyle birlikte verimlilik odaklı bir dönüşüm geçirmiştir. Bu çalışma, 2024–2025 normal sezonuna ait 1.230 maçlık kapsamlı veri setini inceleyerek, modern NBA’de takım başarısını (Win%) belirleyen kritik oyun türü (playtype) dinamiklerini ortaya koymayı amaçlamaktadır. Analiz sürecinde on farklı hücum aksiyonu; verimlilik, kullanım sıklığı ve hata payı parametreleri çerçevesinde Random Forest regresyonu ve korelasyon analizleri ile değerlendirilmiştir. Random Forest modeli sonuçlarına göre, takım başarısını en güçlü şekilde öngören değişken %16,9 önem derecesiyle Spot Up eFG% (Efektif Şut Yüzdesi) olarak belirlenmiş; bunu sırasıyla Spot Up FG% (%15,2) ve Transition (Geçiş Hücumu) TOV FREQ% (Top Kaybı Oranı) (%15,2) izlemiştir. Korelasyon analizleri, Pick and Roll Top Yönlendiricilerin (Ball Handler) pozisyon başına sayı (PPP) oranı (r = 0,714) ve Spot Up eFG% (r = 0,648) ile başarı arasında güçlü pozitif ilişkiler saptarken, Transition top kaybı sıklığının (r = -0,578) performansı en olumsuz etkileyen unsur olduğunu kanıtlamıştır. Dört alanlı (quadrant) değerlendirme; Cut (Kat) ve Transition aksiyonlarının "Verimli ve Sık Kullanılan" kategorisinde yer aldığını, buna karşın Isolation ve Handoff gibi bireysel temelli oyunların düşük verimlilik sunduğunu ortaya koymuştur. Sonuç olarak bulgular, elit hücum performansının sadece yüksek hacimli oyunlara değil, özellikle alan paylaşımına dayalı Spot Up fırsatlarının optimize edilmesine ve geçiş hücumlarında karar verme süreçlerinin disipline edilmesine bağlı olduğunu göstermektedir.

Anahtar Kelimeler

• Hücum Verimliliği
• Oyun Türü Analizi
• NBA
• Makine Öğrenmesi

PLAYTYPE DYNAMICS OF OFFENSIVE EFFICIENCY IN MODERN BASKETBALL

Öz

Offensive strategies in the NBA have undergone a significant transformation toward efficiency-driven models through analytical evolution. This study aims to identify the critical playtype dynamics determining team success (Win%) in the modern NBA by examining a comprehensive dataset of 1,230 games from the 2024–2025 regular season. Ten distinct offensive actions were evaluated across parameters of efficiency, frequency, and error rates using Random Forest regression and correlation analyses. Random Forest modeling identified eFG% from Spot Up plays as the most influential predictor of winning percentage with an importance value of 16.9%, followed by Spot Up FG% (15.2%) and Turnover Frequency (TOV FREQ%) in Transition (15.2%). Correlation results demonstrated strong positive relationships between Pick and Roll Ball Handler PPP (r = 0.714), Spot Up eFG% (r = 0.648), and team success, while turnover frequency during transition (r = -0.578) was identified as the most significant negative performance driver. Quadrant analysis categorized Cut and Transition actions as "Efficient & Frequent," whereas individual-based plays such as Isolation and Handoff exhibited lower efficiency. Collectively, the findings indicate that elite offensive performance depends not merely on high-volume play execution, but specifically on the optimization of spacing-dependent Spot Up opportunities and the disciplined management of decision-making processes during transition phases.

Anahtar Kelimeler

• Offensive Efficiency
• Playtype Analysis
• NBA
• Machine Learning

Kaynakça

1. Alonso-Pérez-Chao, E., Salazar, H., Bustamante-Sánchez, Á., Sansone, P., & Lorenzo, A. (2025). Identifying winning strategies: analysis of play-types in professional European basketball leagues. International Journal of Performance Analysis in Sport, 25(6), 1047–1058. https://doi.org/10.1080/24748668.2025.2487324
2. Amatria, M., Iván-Baragaño, I., Losada, J. L., & Maneiro, R. (2025). Analysis of the use, effectiveness, and efficiency of the pick and roll in elite women’s basketball. Frontiers in Sports and Active Living, 7, 1553270. https://doi.org/10.3389/fspor.2025.1553270
3. Bustamante-Sánchez, A., Gomez-Ruano, M.-A., Clemente-Suárez, V. J., & Jiménez-Sáiz, S. L. (2022). Pre-shot combinations and game-related statistics discriminating between winners and losers depending on the game location during the NBA COVID-19 season. Frontiers in Physiology, 13, 949445. https://doi.org/10.3389/fphys.2022.949445
4. Chang, Y.-H., Maheswaran, R., Su, J., Kwok, S., Levy, T., Wexler, A., & Squire, K. (2014). Quantifying shot quality in the NBA. In Proceedings of the 8th Annual MIT Sloan Sports Analytics Conference. MIT, Boston, MA. Christmann, J., Akamphuber, M., Müllenbach, A. L., & Güllich, A. (2018). Crunch time in the NBA: The effectiveness of different play types in the endgame of close matches in professional basketball. International Journal of Sports Science & Coaching, 13(6), 1090–1099. https://doi.org/10.1177/1747954118772485
5. Ciampolini, V., do Nascimento, J. V., Ibáñez, S. J., de Oliveira Nicolazzi, L., Camaroto, M., Rocha, J. C. S., & Saad, M. A. (2018). Análise técnico-tática ofensiva de equipes finalistas da NBA: Um estudo de caso. Journal of Physical Education, 29(1) https://doi.org/10.4025/jphyseduc.v29i1.2931
6. Cohen, J. (2013). Statistical power analysis for the behavioral sciences (2nd ed.). Routledge. Courel-Ibáñez, J., McRobert, A. P., Ortega Toro, E., & Cárdenas Vélez, D. (2018). Inside game effectiveness in NBA basketball: Analysis of collective interactions. Kinesiology, 50(2), 218–227. https://doi.org/10.26582/k.50.2.5
7. Dong, R., Chen, R., Zhang, S., Sansone, P., Mateus, N., & Liu, H. (2026). Beyond the box score: Clustering offensive play types to reveal game styles in professional basketball. Journal of Sports Sciences, 44(3), 357–371. https://doi.org/10.1080/02640414.2025.2578585
8. Erdeveciler, Ö. (2023). Game trends of the Turkish Basketball Super League. SPORMETRE Beden Eğitimi ve Spor Bilimleri Dergisi, 21(4), 121–128. https://doi.org/10.33689/spormetre.1363054

9. Ertetik, G., Durmuş, T., Erdeveciler, Ö., & Ersöz, G. (2021). Basketbolun değişen oyun yapısı: NBA ve Euroleague örnekleri. Avrasya Spor Bilimleri ve Eğitim Dergisi, 3(1), 81–95. https://doi.org/10.47778/ejsse.907049
10. Gong, Z., & Li, Y. (2025). The evolution and future of NBA game style. Finance & Economics 3(1). https://doi.org/10.61173/sft7ah13
11. Gou, H., & Zhang, H. (2022). Better offensive strategy in basketball: A two-point or a three-point shot? Journal of Human Kinetics, 83, 287–299. https://doi.org/10.2478/hukin-2022-0061
12. Hu, Q. (2024). The three-point revolution: A profound impact on NBA game strategy. Science and Technology of Engineering, Chemistry and Environmental Protection, 2(4), 1–8. https://doi.org/10.61173/z7hr2s25
13. Ichikawa, J., Yamada, M., & Fujii, K. (2025). Analyzing coordinated group behavior through role-sharing: A pilot study in female 3-on-3 basketball with practical application. Frontiers in Sports and Active Living, 7, 1513982. https://doi.org/10.3389/fspor.2025.1513982
14. Lamas, L., Santana, F., Heiner, M., Ugrinowitsch, C., & Fellingham, G. (2015). Modeling the offensive-defensive interaction and resulting outcomes in basketball. PLOS ONE, 10(12). https://doi.org/10.1371/journal.pone.0144435
15. Marmarinos, C., Apostolidis, N., Kostopoulos, N., & Apostolidis, A. (2016). Efficacy of the “pick and roll” offense in top level European basketball teams. Journal of Human Kinetics, 51, 121–131. https://doi.org/10.1515/hukin-2015-0176 Matulaitis, K., & Bietkis, T. (2021). Prediction of offensive possession ends in elite basketball teams. International Journal of Environmental Research and Public Health, 18(3), 1083. https://doi.org/10.3390/ijerph18031083
16. McLean, B. D., Strack, D., Russell, J., & Coutts, A. J. (2019). Quantifying physical demands in the National Basketball Association: Challenges around developing best-practice models for athlete care and performance. International Journal of Sports Physiology and Performance, 14(4), 414–420. https://doi.org/10.1123/ijspp.2018-0384
17. Poropudas, J., & Halme, T. (2023). Dean Oliver's four factors revisited. arXiv preprint. https://doi.org/10.48550/arXiv.2305.13032
18. Ruiz, M., Martinez, J. A., López-Hernández, F. A., & Castellano, A. (2014). The relationship between concentration of scoring and offensive efficiency in the NBA. Journal of Quantitative Analysis in Sports, 10(1), 27–36. https://doi.org/10.1515/jqas-2013-0060
19. Sandholtz, N., Mortensen, J., & Bornn, L. (2020). Measuring spatial allocative efficiency in basketball. Journal of Quantitative Analysis in Sports, 16(4), 271–289. https://doi.org/10.1515/jqas-2019-0126
20. Schober, P., Boer, C., & Schwarte, L. A. (2018). Correlation coefficients: Appropriate use and interpretation. Anesthesia & Analgesia, 126(5), 1763–1768. https://doi.org/10.1213/ane.0000000000002864
21. Supola, B., Hoch, T., & Baca, A. (2023). Modeling the formation of defensive gaps in basketball: Cutting on a teammate’s drive. PLOS ONE, 18(2). https://doi.org/10.1371/journal.pone.0281467
22. Vázquez-Estévez, C., Prieto-Lage, I., Reguera-López-de-la-Osa, X., Gutiérrez-Santiago, J. A., Toledo-González, M., & Gutiérrez-Santiago, A. (2025). Offensive patterns and performance analysis in one-possession scenarios during the last minute and overtime in the EuroLeague. Applied Sciences, 15(4), 1928. https://doi.org/10.3390/app15041928
23. Yu, A., & Chung, S.S. (2019). Framework for Analysis and Prediction of NBA Basketball Plays: On-Ball Screens. 2019 IEEE SmartWorld, Ubiquitous Intelligence & Computing, Advanced & Trusted Computing, Scalable Computing & Communications, Cloud & Big Data Computing, Internet of People and Smart City Innovation (SmartWorld/SCALCOM/UIC/ATC/CBDCom/IOP/SCI), Leicester, UK, 1384-1391.
24. Zhang, S., Lorenzo, A., Woods, C. T., Leicht, A. S., & Gomez, M.-A. (2019). Evolution of game-play characteristics within-season for the National Basketball Association. International Journal of Sports Science & Coaching, 14(3), 355–362. https://doi.org/10.1177/17479541198471