2022 FIBA 남자농구 아시안컵 경기결과를 활용한 머신러닝 분류 모형의 예측 성능 비교 = Comparison of Prediction Performance of Machine Learning Classification Model Using 2022 FIBA Men's Basketball Asian Cup Match Results

다국어 초록 (Multilingual Abstract)

The purpose of this study is to compare predictive performance using traditional statistical methods, data mining techniques, and machine learning techniques using the box scores of the 2022 FIBA Men's Basketball Asian Cup Games. The subject of this study was a total of 72 match records among the records obtained through the official records of the 2022 FIBA Men's Basketball Asian Cup, and the outcome of the match was predicted through a total of 20 variables. Five classification models were used to predict the outcome of the men's basketball Asian Cup competition: K Nearest Neighbor (KNN), Decision Tree, Support Vector Machine (SVM), Logistic Regression, and Random Forest. For the data collection and processing of this study, the statistical program Python 3.10.1 version was used together with the library, and the results obtained are as follows. First, in the prediction results for each model, the SVM model showed the optimal prediction performance than the KNN, Decision Tree, Random Forest, and Logistic Regression models, and showed 86.67% prediction accuracy and 0.868 F1 score. Second, when the Random Forest classification model was used to predict the win/loss result of the 2022 Men's Basketball Asian Cup, overfitting occurred because the number of samples in the data set was not sufficient. Based on the results of this study, it was considered that more data by increasing the number of cases in the future can increase the accuracy of the model and reduce the possibility of overfitting. And in order to obtain more accurate prediction results, it is judged that research related to deep learning as well as machine learning is necessary.

국문 초록 (Abstract)

이 연구의 목적은 2022 FIBA 남자농구 아시아컵 경기대회의 공식기록(box score)을 사용하여 전통적 측면 에서의 통계적 방법, 데이터마이닝 기법, 머신러닝의 기법을 활용하여 예측 성능을 비교한 것이다. 본 연구의 대 상은 2022 FIBA 남자농구 아시아컵 경기대회의 공식기록을 통해 얻어지는 기록 중에서 총 72개 경기기록이었 으며, 총 20개의 변수를 통해 경기 승패 결과 예측을 하였다. 남자농구 아시아컵 경기대회의 승패 결과를 예측 하기 위해 KNN(K Nearest Neighbor), Decision Tree, Support Vector Machine(SVM), Logistic Regression, Random Forest 5가지 분류 모델을 사용하였다. 이 연구의 자료수집과 처리를 위하여 통계프로그 램 Python 3.10.1 버전을 라이브러리와 함께 사용하였고, 얻은 결과는 다음과 같다. 첫째, 모델별 예측 결과에 서는 SVM 모델이 KNN, Decision Tree, Random Forest, Logistic Regression 모델보다 최적의 예측 성능 을 나타냈고 86.67%의 예측 정확도 및 0.868의 F1 점수를 보였다. 둘째, Random Forest 분류 모델을 이용 하여 2022 남자농구 아시아컵 경기대회의 승패 결과를 예측했을 때, 데이터 세트의 샘플 개수가 충분하지 않기 때문에 과적화(Overfitting) 현상이 발생했다. 이 연구의 연구 결과를 토대로 향후 사례 수를 증가하여 더 많은 데이터가 모델의 정확도를 높이는 동시에 과적합 가능성을 줄일 수 있다고 사료되었다. 그리고 더 정확한 예측 결과를 얻기 위하여서 머신러닝뿐만 아니라 딥러닝과 관련한 연구도 필요할 것으로 판단되는 바이다.

참고문헌 (Reference)

• 1 장효진 ; 곽현 ; 최승회, "회귀모형을 이용한 한국프로농구 승부결과 분석" 한국지능시스템학회 25 (25): 489-494, 2015
• 2 김세형 ; 박재현 ; 김혜진 ; 강상조, "한국프로농구 경기기록 분석에 의한 승패결정요인" 한국체육측정평가학회 10 (10): 1-12, 2008
• 3 최형준 ; 이윤수, "축구 월드컵대회의 경기기록 기반 경기결과 예측" 한국체육과학회 28 (28): 1317-1325, 2019
• 4 박상찬, "제4차 산업혁명과 데이터 과학" 15 (15): 21-28, 2017
• 5 최형준 ; 김주학, "인공신경망(Artificial Neural Network)을 이용한 2005년도 영국 윔블던 테니스 대회의 경기결과 예측에 관한 연구" 한국체육학회 45 (45): 459-468, 2006
• 6 조정환, "스포츠 빅데이터 활용과 전망" 한국체육측정평가학회 14 (14): 01-11, 2012
• 7 허종관 ; 김세중 ; 도재현, "로지스틱/마르코프 체인 모델을 이용한 한국프로농구 순위 예측" 한국체육과학회 25 (25): 1269-1276, 2016
• 8 최형준, "국내 스포츠 빅데이터 분석 연구의 현황" 한국체육측정평가학회 22 (22): 63-69, 2020
• 9 구승환 ; 김현수 ; 장성용, "국내 남자 프로농구 승패 예측 모형 비교 연구" 국민체육진흥공단 한국스포츠정책과학원 20 (20): 704-711, 2009
• 10 Miljković, D., "he use of data mining for basketball matches outcomes prediction" 2010
• 11 Horvat, T., "The use of machine learning in sport outcome prediction: A review" 10 (10): 138-151, 2020
• 12 Vapnik, V. N., "The nature of statistical learning theory" Springer 232-233, 1995
• 13 Horvat, T., "The impact of selecting a validation method in machine learning on predicting basketball game outcomes" 12 (12): 431-, 2020
• 14 Ye, N., "The handbook of Data Mining" Lawrence Erlbaum Associates 125-126, 2003
• 15 Nguyen, N. H., "The application of machine learning and deep learning in sport:predicting NBA players’ performance and popularity" 1-19, 2021
• 16 Bunker, R., "The Application of Machine Learning Techniques for Predicting Match Results in Team Sport : A Review" 73 : 1285-1322, 2022
• 17 Cortes, C., "Support-vector networks" 20 (20): 273-297, 1995
• 18 Drucker, H., "Support vector regression machines" 9 (9): 155-161, 1997
• 19 Dubbs, A., "Statistics-free sports prediction" 13 (13): 173-181, 2018
• 20 Zhao, Y., "Sports enterprise marketing and financial risk management based on decision tree and data mining" 8 (8): 2-7, 2021
• 21 Cao, C., "Sports data mining technology used in basket ball outcome prediction" Dublin Institute of Technology 2012
• 22 Bromley, J., "Signature verification using a"siamese"time delay neural network" 7 (7): 669-688, 1993
• 23 Tanha, J., "Semi-supervised self-training for decision tree classifiers" 8 (8): 355-370, 2017
• 24 Torres, R. A., "Prediction of NBA games based on Machine Learning Methods" University of Wisconsin 2013
• 25 Liu, Y., "Prediction for NCAA championship" 8-14, 2021
• 26 WentingWang, R. M., "Predicting winners of NCAA women’s basketball tournament games" 4 (4): 173-180, 2014
• 27 Chovanec, P., "Predicting winners in the NCAA Basketball Tournament" Kansas State Universiteit 2021
• 28 Levandoski, A., "Predicting the NCAA Men’s Basketball Tournament with Machine Learning" 1-15, 2017
• 29 Yezus, A., "Predicting outcome of soccer matches using machine learning" Saint Petersburg University 2014
• 30 Prasetio, D., "Predicting football match results with logistic regression" 16-19, 2016
• 31 Zimmermann, A., "Predicting college basketball match outcomes using machine learning techniques: some results and lessons learned"
• 32 Maier, T., "Predicting biathlon shooting performance using machine learning" 36 (36): 2333-2339, 2018
• 33 Soliman, G., "Predicting all star player in the national basketball association using random forest" IEEE 706-713, 2017
• 34 Lin, J., "Predicting National Basketball Association winners" 2014
• 35 Kannan, A., "Predicting National Basketball Association success: A machine learning approach" 1 (1): 7-, 2018
• 36 Jin, M., "Predication of different stages of Alzheimer’s disease using neighborhood component analysis and ensemble decision tree" 302 (302): 35-41, 2018
• 37 Mueller, S. Q., "Pre-and within-season attendance fore casting in Major League Baseball: a random forest approach" 52 (52): 4512-4528, 2020
• 38 Osei-Bryson, K. M., "Post-pruning in decision tree induction using multiple performance measures" 34 (34): 3331-3345, 2007
• 39 Bishop, C. M., "Pattern recognition and machine learning" springer 2006
• 40 Lam, M. W., "One-match-ahead forecasting in two-team sports with stacked Bayesian regressions" 8 (8): 87-99, 2018
• 41 Purucker, M. C., "Neural network quarterbacking" 15 : 9-15, 1996
• 42 Kravanja, A., "Napovedanje zmagovalcev košarkaških tekem" University of Ljubljana 2013
• 43 Thabtah, F., "NBA game result prediction using feature analysis and machine learning" 6 (6): 103-, 2019
• 44 Song, K., "Modelling the scores and performance statistics of NBA basketball games" 49 (49): 2604-2616, 2020
• 45 Luu, B. C., "Machine learning outperforms logistic regression analysis to predict next-season NHL player injury: an analysis of 2322 players from 2007 to 2017" 8 (8): 2325967120953404-, 2020
• 46 Suthaharan, S., "Machine learning models and algorithms for big data classification" 36 (36): 1-12, 2016
• 47 Jain, S., "Machine learning approaches to predict basketball game outcome" IEEE: The Institute of Electrical and Electronics 1-7, 2017
• 48 Harrington, P., "Machine Learning in Action" Manning Publications Co 2012
• 49 Schölkopf, B., "Learning with kernels: support vector machines, regularization, optimization, and beyond" MIT Press 96-97, 2002
• 50 Niblett, T., "Learning decision rules in noisy domains" the 6th Annual Technical Conference on Research and development in expert systems III 25-34, 1987
• 51 Alpydin, E., "Introduction to machine learning (2nd ed.)" MIT Press 201-205, 2010
• 52 Passi, K., "Increased Prediction Accuracy in the Game of Cricket using Machine Learning"
• 53 Chen, W. J., "Hybrid basketball game outcome prediction model by integrating data mining methods for the national basket-ball association" 23 (23): 477-, 2021
• 54 Nedellec, R., "GEFCom2012 : Electric load forecasting and backcasting with semi-parametric models" 30 (30): 375-381, 2014
• 55 Sagi, O., "Ensemble learning: A survey" 8 (8): e1249-, 2018
• 56 Mendes-Moreira, J., "Ensemble approaches for regression : A survey" 45 (45): 1-40, 2012
• 57 Madarame, H., "Defensive rebounds discriminate winners from losers in European but not in Asian women’s basketball championships" 9 (9): 13-18, 2018
• 58 Mendonça, L. F., "Decision tree search methods in fuzzy modeling and classification" 44 (44): 106-123, 2007
• 59 Han, J., "Data mining: concepts and techniques" Morgan Kaufman Publishers 2012
• 60 Jadhav, S. D., "Comparative study of K-NN, naive Bayes and decision tree classification techniques" 5 (5): 1842-1845, 2016
• 61 Noor, N. B., "Comparative Study Between Decision Tree, SVM and KNN to Predict Anaemic Condition" 24-28, 2019
• 62 Hassonah, M. A., "Churn Prediction: A Comparative Study Using KNN and Decision Trees" IEEE: the Institute of Electrical and Electronics 182-186, 2019
• 63 Tichy, W., "Changing the Game: Dr. Dave Schrader on sports analytics" Ubiquity 1-10, 2016
• 64 Lieder, N., "Can machine-learning methods predict the outcome of an NBA game?" 2018
• 65 Lopez, M. J., "Building an NCAA men’s basketball predictive model and quantifying its success" 11 (11): 5-12, 2015
• 66 Johnson, K. C., "Blood pressure measurement in SPRINT (systolic blood pressure intervention trial)" 71 (71): 848-857, 2018
• 67 Zuccolotto, P., "Big data analytics for modelling scoring probability in basketball:The effect of shooting under high-pressure conditions" 13 (13): 569-589, 2018
• 68 Russell, S., "Artificial Intelligence : A Modern Approach" Prentice Hall 2002
• 69 Hosmer, D. W., "Applied Logistic Regression" John Wiley&Sons Inc 2000
• 70 Pathak, N., "Applications of modern classification techniques to predict the outcome of ODI cricket" 87 (87): 55-60, 2016
• 71 Korhonen, K. T., "Application of nearest‐neighbour regression for generalizing sample tree information" 12 (12): 97-101, 1997
• 72 Li, B., "Application of artificial intelligence in basketball sport" 11 (11): 54-67, 2021
• 73 Pai, P. F., "Analyzing bas ketball games by a support vector machines with decision tree model" 28 (28): 4159-4167, 2017
• 74 Lessmann, S., "Alternative methods of predicting competitive events : An applica"tion in horserace betting markets" 26 (26): 518-536, 2010
• 75 Boser, B. E., "A training al gorithm for optimal margin classifiers" 144-152, 1992
• 76 Haghighat, M., "A review of data mining techniques for result prediction in sports" 2 (2): 7-12, 2013
• 77 Ballı, S., "A novel method for prediction of EuroLeague game results using hybrid feature ex traction and machine learning techniques" 150 : 111119-, 2021
• 78 Bunker, R. P., "A machine learning frame"work for sport result prediction" 15 (15): 27-33, 2019
• 79 Groll, A., "A hybrid random forest to predict soccer matches in international tournaments" 15 (15): 271-287, 2019
• 80 Cai, W., "A hybrid ensemble learning framework for basketball outcomes prediction" 528 : 121461-, 2019
• 81 Gu, W., "A game-predicting expert system using big data and machine learning" 130 : 293-305, 2019
• 82 Li, Y., "A data-driven prediction ap proach for sports team performance and its application to National Basketball Association" 98 : 102123-, 2021
• 83 Elish, M. O., "A comparative study of fault density prediction in aspect-oriented systems using MLP, RBF, KNN, RT, DENFIS and SVR models" 42 (42): 695-703, 2014
• 84 저우차우 ; 최형준, "2019 세계 남자 농구 월드컵 경기대회의 공식기록에 기반한 경기내용에 관한 군집 분석" 한국체육학회 59 (59): 397-411, 2020