LCCspm: l-Length Closed Contiguous Sequential Patterns Mining Algorithm to Find Frequent Athlete Movement Patterns from GPS

The analysis of athletes’ spatiotemporal data provides actionable insights for strength and conditioning and customized training designs. The identification of unique movements and adjacent match events of team-sport athletes is important. It helps to understand the demands of a match and to advance training programs by improving training specificity. In this paper we present a novel l-length Closed Contiguous sequential pattern mining (LCCspm) algorithm. To validate LCCspm, England Rugby Football League (RFL) Super League players’ movements and Fédération Internationale de Football Association (FIFA) 2018 football world cup events datasets were used. The algorithm was compared with the other existing algorithm (i.e., CCspan). Empirically, the most frequently discovered closed contiguous patterns from RFL were 1-7 length movement patterns while 10-40 length patterns were those discovered in men’s FIFA 2018 world cup. This reflects the duration at which RFL and FIFA football match events usually occur and how data granularity influence results. LCCspm greatly outperforms the CCSpan in terms of scalability, runtime and memory usage. The use of LCCspm instead of CCspan for mining closed contiguous sequences regardless of the length of patterns and size of the database is recommended as it offers timely retrieval of patterns with lesser compute.