Abstract: Preference time in a triathlon denotes the time that is planned to be achieved by an athlete in a particular competition. Usually, the preference time is calculated some days, weeks, or even months before the competition. Mostly, trainers calculate the proposed preference time according to the current form, body performances of athletes, psychological abilities and their health state. They also take course specifications into account in order to make their proposal as exact as possible. However, until recently, this prediction was performed manually. This paper presents an automatic framework for modeling preference times based on previous results of athletes on a particular racecourse and particle swarm optimization. Indeed, the framework observed the problem as optimization, where the goal is to find such preference time that is as much as possible correlated with past data. Practical experiments with different scenarios reveal that the proposed solution is promising.
