Reproduce “STGCN-LSTM for Olympic Medal Prediction: Dynamic Power Modeling and Causal Policy Optimization” on OpenResearch

Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.

Universal app for Apple silicon and Intel. Requires macOS 11 or later.

About this paper

Yiquan Wang, Jiaying Wang, Tin-Yeh Huang, Jingyi Yang, Zihao Xu

A research team developed a hybrid STGCN-LSTM model integrated with a Zero-Inflated Compound Poisson framework to predict national Olympic medal distributions and inform policy optimization. The model forecasts outcomes for the 2028 Los Angeles Olympics, identifies emerging medal-winning countries, and quantifies the causal impact of factors like coaching and hosting on medal counts.

Key insights

  • An 'inverted U-shaped' relationship describes the influence of a country's economic development on its Olympic medal growth, with optimal growth observed within a specific GDP range.
  • The causal impact of hosting the Olympic Games can be decomposed into direct and indirect effects, mediated by factors like infrastructure investment and youth participation.
  • The marginal contribution of 'great coaches' can be quantified, showing that their benefits peak over 2-3 Olympic cycles before diminishing, highlighting the need for dynamic recruitment strategies.

Summary by alphaXiv.

Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.