Summary of Mlfef: Machine Learning Fusion Model with Empirical Formula to Explore the Momentum in Competitive Sports, by Ruixin Peng et al.
MLFEF: Machine Learning Fusion Model with Empirical Formula to Explore the Momentum in Competitive Sports
by Ruixin Peng, Ziqing Li
First submitted to arxiv on: 19 Feb 2024
Categories
- Main: Machine Learning (cs.LG)
- Secondary: None
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary This paper explores the concept of momentum in tennis matches, aiming to develop a framework for real-time analysis. The authors utilize Grand Slam men’s singles match data from recent years and build two models: a data-driven model incorporating SVM, Random Forest, and XGBoost algorithms; and an empirical formula-based model. The data-driven model involves preprocessing, feature engineering, and fusion of the three aforementioned algorithms. In contrast, the mechanism analysis model selects important features based on tennis players’ and enthusiasts’ suggestions, using the sliding window algorithm to calculate weights and visualizing momentum. To analyze momentum fluctuations, the authors employ the CUMSUM algorithm and RUN Test, concluding that momentum is not random and trends might be random. Finally, they conduct a Monte Carlo simulation to evaluate the robustness of the fusion model. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This paper tries to understand what makes tennis players win or lose over time. It looks at data from many matches and creates two ways to measure this “momentum.” One way is based on computer algorithms like SVM, Random Forest, and XGBoost. The other way uses rules that experts think are important for momentum. They test these models using old match data and find that momentum can’t be fully explained by random chance. Instead, there might be patterns or trends. To make sure their results aren’t just luck, they simulate many different scenarios to see how the model would work in each one. |
Keywords
* Artificial intelligence * Feature engineering * Random forest * Xgboost
