This paper introduces a martingale that characterizes two properties of evolving forecast distributions. Ideal forecasts of a future event behave as martingales, sequentially updating the forecast to leverage the available information as the future event approaches. The threshold martingale introduced here measures the proportion of the forecast distribution lying below a threshold. In addition to being calibrated, a threshold martingale has quadratic variation that accumulates to a total determined by a quantile of the initial forecast distribution. Deviations from calibration or total volatility signal problems in the underlying model. Calibration adjustments are well-known, and we augment these by introducing a martingale filter that improves volatility while guaranteeing smaller mean squared error. Thus, post-processing can rectify problems with calibration and volatility without revisiting the original forecasting model. We apply threshold martingales first to forecasts from simulated models and then to models that predict the winner in professional basketball games. ∗All correspondence regarding this manuscript should be directed to Prof. Stine at the address shown with the title. He can be reached via e-mail at stine@wharton.upenn.edu.
[1]
Lawrence M. Wein,et al.
Analysis of a Forecasting-Production-Inventory System with Stationary Demand
,
2001,
Manag. Sci..
[2]
Dean P. Foster,et al.
Variable Selection in Data Mining: Building a Predictive Model for Bankruptcy
,
2001
.
[3]
Jian Shi,et al.
Modelling the scores and performance statistics of NBA basketball games
,
2018,
Commun. Stat. Simul. Comput..
[4]
Hal S. Stern,et al.
A Brownian Motion Model for the Progress of Sports Scores
,
1994
.
[5]
Frederick Mosteller,et al.
Predicting Professional Sports Game Outcomes from Intermediate Game Scores
,
1992
.
[6]
Kai Song,et al.
A discrete-time and finite-state Markov chain based in-play prediction model for NBA basketball matches
,
2019,
Commun. Stat. Simul. Comput..
[7]
D. Heath,et al.
Modelling the evolution of demand forecasts with application to safety stock analysis in production distribution systems
,
1994
.