스포츠베팅 | Cases and Studies in Sports Betting | 体育博彩
- date : 2015-05-20 01:10|hit : 2544
-
- Article] Forecasting in the NBA and Other Team Sports: Network Effects in Action
-
DocNo of ILP: 1086
Doc. Type: Article
Title: Forecasting in the NBA and Other Team Sports: Network Effects in Action
Authors: de Melo, POSV; Almeida, VAF; Loureiro, AAF; Faloutsos, C
Full Name of Authors: Vaz de Melo, Pedro O. S.; Almeida, Virgilio A. F.; Loureiro, Antonio A. F.; Faloutsos, Christos
Keywords by Author: Complex networks; social networks; sports analytics
Keywords Plus: PREDICTION MARKETS; ACCURACY
Abstract: The multi-million sports-betting market is based on the fact that the task of predicting the outcome of a sports event is very hard. Even with the aid of an uncountable number of descriptive statistics and background information, only a few can correctly guess the outcome of a game or a league. In this work, our approach is to move away from the traditional way of predicting sports events, and instead to model sports leagues as networks of players and teams where the only information available is the work relationships among them. We propose two network-based models to predict the behavior of teams in sports leagues. These models are parameter-free, that is, they do not have a single parameter, and moreover are sport-agnostic: they can be applied directly to any team sports league. First, we view a sports league as a network in evolution, and we infer the implicit feedback behind network changes and properties over the years. Then, we use this knowledge to construct the network-based prediction models, which can, with a significantly high probability, indicate how well a team will perform over a season. We compare our proposed models with other prediction models in two of the most popular sports leagues: the National Basketball Association (NBA) and the Major League Baseball (MLB). Our model shows consistently good results in comparison with the other models and, relying upon the network properties of the teams, we achieved a approximate to 14% rank prediction accuracy improvement over our best competitor.
Cate of OECD: Computer and information sciences
Year of Publication: 2012
Business Area: game
Detail Business: game
Country: USA
Study Area:
Name of Journal: ACM TRANSACTIONS ON KNOWLEDGE DISCOVERY FROM DATA
Language: English
Country of Authors: [Vaz de Melo, Pedro O. S.; Almeida, Virgilio A. F.; Loureiro, Antonio A. F.] Univ Fed Minas Gerais, Belo Horizonte, MG, Brazil; [Faloutsos, Christos] Carnegie Mellon Univ, Pittsburgh, PA 15213 USA
Press Adress: de Melo, POSV (reprint author), Univ Fed Minas Gerais, Belo Horizonte, MG, Brazil.
Email Address: pedro.olmo@gmail.com
Citaion:
Funding:
Lists of Citation: ABBOT H., 2007, TRUE HOOP; BARZILAI A., 2008, ADJUSTED PLUS MINUS; BEN_NAIM E., 2007, J QUANT ANAL SPORTS, V2, P1; BRADLEY R., 2009, LABOR PAINS NOTHING; COWAN C., 2006, BUSINESS WEEK; DA COSTA J P, 2004, AUSTR NZ J STAT, V47 , P515; DILGER A., 2002, SSRN ELIBRARY; EASTERBROOK G., 2006, ESPN; FAST A., 2006, P AAAI FALL S CAPT U; FESSLER JA, 1994, IEEE T SIGNAL PROCES, V42, P2664, DOI 10.1109/78.324732; Girvan M, 2002, P NATL ACAD SCI USA, V99, P7821, DOI 10.1073/pnas.122653799; HAMBACH W., 2006, GAMING LAW REV, V10, P6; ILARDI S., 2007, ADJUSTED PLUS MINUS; Kelly D., 2003, SIGIR Forum, V37; Kendall M. G., 1990, RANK CORRELATION MET; LAHMAN S., 2008, LAHMAN BASEBALL DATA; LEWIS M., 2009, NY TIMES; LIGHTMAN A., 2010, OPEN PREDICTION SPOR; LOONEY D. S., 1976, SPORTS ILLUSTRATED; Luckner S, 2008, LECT NOTES BUS INF, V2, P227; Neville J., 2005, P 11 ACM SIGKDD INT, P449, DOI DOI 10.1145/1081870.1081922; NEWMAN M., 2010, ACM T EMBED COMPUT S, V9 , P4; Nichols D., 1998, P 5 DELOS WORKSH FIL, P31; Onody RN, 2004, PHYS REV E, V70, DOI 10.1103/PhysRevE.70.037103; PAGE G., 2007, J QUANT ANAL SPORTS, V3 , P1; Pandit S., 2007, P 16 INT C WORLD WID, P201, DOI 10.1145/1242572.1242600; Park J., 2005, J STAT MECH-THEORY E, V10; PAULSEN J., 2006, EFFICIENCY PER MINUT; REHEUSER R, 2010, NBA ENCY; ROSENBAUM D. T., 2004, MEASURING NBA PLAYER; Shetty J., 2005, P 3 INT WORKSH LINK, P74, DOI 10.1145/1134271.1134282; Spann M, 2009, J FORECASTING, V28, P55, DOI 10.1002/for.1091; Stekler HO, 2010, INT J FORECASTING, V26, P606, DOI 10.1016/j.ijforecast.2010.01.003; Vaz de Melo P. O., 2008, P ACM INT C KNOWL DI, P695; WEINBERG A, 2003, CASE LEGAL SPORTS GA
Number of Citaion: 35
Publication: ASSOC COMPUTING MACHINERY
City of Publication: NEW YORK
Address of Publication: 2 PENN PLAZA, STE 701, NEW YORK, NY 10121-0701 USA
ISSN: 1556-4681
29-Character Source Abbreviation: ACM T KNOWL DISCOV D
ISO Source Abbreviation: ACM Trans. Knowl. Discov. Data
Volume: 6
Version: 3
Start of File:
End of File:
DOI: 10.1145/2362383.2362387
Number of Pages: 27
Web of Science Category: Computer Science, Information Systems; Computer Science, Software Engineering
Subject Category: Computer Science
Document Delivery Number: 030HB
Unique Article Identifier: WOS:000310560600004
[이 게시물은 박장호님에 의해 2015-05-20 14:37:00 GAMBLING에서 이동 됨]
- reply : 0
-
- list
-
- prev
- next