A Data Snapshot Approach for Making Real-Time Predictions in Basketball
- 1 June 2018
- journal article
- research article
- Published by SAGE Publications in Big Data
- Vol. 6 (2) , 96-112
Abstract
This article proposes a novel approach, called data snapshots, to generate real-time probabilities of winning for National Basketball Association (NBA) teams while games are being played. The approach takes a snapshot from a live game, identifies historical games that have the same snapshot, and uses the outcomes of these games to calculate the winning probabilities of the teams in this game as the game is underway. Using data obtained from 20 seasons worth of NBA games, we build three models and compare their accuracies to a baseline accuracy. In Model 1, each snapshot includes the point difference between the home and away teams at a given second of the game. In Model 2, each snapshot includes the net team strength in addition to the point difference at a given second. In Model 3, each snapshot includes the rate of score change in addition to the point difference at a given second. The results show that all models perform better than the baseline accuracy, with Model 1 being the best model.Keywords
This publication has 10 references indexed in Scilit:
- Modeling basketball play-by-play dataExpert Systems with Applications, 2016
- Simulating a basketball match with a homogeneous Markov model and forecasting the outcomeInternational Journal of Forecasting, 2012
- Can Losing Lead to Winning?Management Science, 2011
- Making Time-series Classification More Accurate Using Learned Constraints2004
- Late-Game Reversals in Professional Basketball, Football, and HockeyThe American Statistician, 2000
- A Brownian Motion Model for the Progress of Sports ScoresJournal of the American Statistical Association, 1994
- Predicting Professional Sports Game Outcomes from Intermediate Game ScoresCHANCE, 1992
- On the Combination of Forecast Probabilities for Consecutive Precipitation PeriodsWeather and Forecasting, 1990
- A General Framework for Forecast VerificationMonthly Weather Review, 1987
- VERIFICATION OF FORECASTS EXPRESSED IN TERMS OF PROBABILITYMonthly Weather Review, 1950