Beep: Balancing Effectiveness and Efficiency when Finding Multivariate Patterns in Racket Sports

TL;DR

This paper introduces Beep, a novel pattern mining algorithm for racket sports that balances effectiveness and efficiency by discovering multivariate patterns with high correlation and noise tolerance, significantly outperforming existing methods.

Contribution

Beep presents a new encoding scheme and an LSH-based algorithm to efficiently find correlated multivariate patterns with noise tolerance in racket sports data.

Findings

Beep effectively discovers meaningful patterns and noise in racket sports data.

Beep is approximately five times faster than the state-of-the-art algorithm.

The approach improves analysis speed and accuracy for sports performance assessment.

Abstract

Modeling each hit as a multivariate event in racket sports and conducting sequential analysis aids in assessing player/team performance and identifying successful tactics for coaches and analysts. However, the complex correlations among multiple event attributes require pattern mining algorithms to be highly effective and efficient. This paper proposes Beep to discover meaningful multivariate patterns in racket sports. In particular, Beep introduces a new encoding scheme to discover patterns with correlations among multiple attributes and high-level tolerances of noise. Moreover, Beep applies an algorithm based on LSH (Locality-Sensitive Hashing) to accelerate summarizing patterns. We conducted a case study on a table tennis dataset and quantitative experiments on multi-scaled synthetic datasets to compare Beep with the SOTA multivariate pattern mining algorithm. Results showed that Beep can effectively discover patterns and noises to help analysts gain insights. Moreover, Beep was about five times faster than the SOTA algorithm.