{"slug": "horse-racing-as-an-ml-ranking-problem-1-18m-runners-walk-forward-validation-and", "title": "Horse racing as an ML ranking problem: 1.18M runners, walk-forward validation and a very strong market baseline [D]", "summary": "A machine-learning practitioner built a horse-racing ranking model trained on 1.18 million runners and evaluated it with walk-forward validation, finding that the betting market remains a very strong baseline. The project, posted to a machine-learning forum, revisits the statistical modeling approach used by Bill Benter's team for Hong Kong racing. The author reports the market baseline proved difficult to beat.", "body_md": "Hi 👋 long time lurker It’s been a few years since the last post about Horse Racing within this sub. A few years ago I was reading a popular science book and came across the story Bill Benter and the statistical models his team developed for Hong Kong racing. What stayed with me wasn’t simply the ide", "url": "https://wpnews.pro/news/horse-racing-as-an-ml-ranking-problem-1-18m-runners-walk-forward-validation-and", "canonical_source": "https://aiflash.com/news/119144/", "published_at": "2026-09-14 01:00:28+00:00", "updated_at": "2026-09-14 01:25:51.020866+00:00", "lang": "en", "topics": ["machine-learning", "ai-research"], "entities": ["Bill Benter"], "alternates": {"html": "https://wpnews.pro/news/horse-racing-as-an-ml-ranking-problem-1-18m-runners-walk-forward-validation-and", "markdown": "https://wpnews.pro/news/horse-racing-as-an-ml-ranking-problem-1-18m-runners-walk-forward-validation-and.md", "text": "https://wpnews.pro/news/horse-racing-as-an-ml-ranking-problem-1-18m-runners-walk-forward-validation-and.txt", "jsonld": "https://wpnews.pro/news/horse-racing-as-an-ml-ranking-problem-1-18m-runners-walk-forward-validation-and.jsonld"}}