درباره این اپیزود

انگلیسی
ایالات متحده آمریکا

رونوشت 🔗

جستجوی اپیزودهای گذشته

اپیزودهای قبلی Data Science in the Wild را جستجو کن.

قسمت های دیگر در این پادکست

Should you recalibrate CTR models on fresh data? Rui Liu's Avazu study: a 6-hour Platt/isotonic refit made calibration worse in about a third of applications. Key takeaways: Random splits flatter calibration. On Avazu (40.4M impressions; LR, DeepFM, DCN-v2), a random split reported LR's ECE at 55–…
Can you ship an LLM change on evals alone? Spotify's Mårten Schultzberg: only if eval effects predict A/B results. On 183 Upworthy tests, his gate ships none. Key takeaways: The question. Judge–human agreement doesn't tell you which changes can skip an A/B test. That needs trial-level surrogacy: e…
Is difference-in-differences broken? Brown economist Peter Hull used AI agents to replicate 1,346 staggered-adoption results from 108 papers: TWFE and modern DiD estimates correlate about 0.9, and significant sign flips are rare. Key takeaways: The worry. In staggered rollouts, two-way fixed effec…
Do LLM recommenders pick by position? A University of Granada study ran 40,000 shuffled prompts through 8 open models, and every one failed both statistical tests for position independence. Key takeaways: Order matters for every model. On a RAG testbed (50,000 Amazon products, 2,000 queries × 20 o…
سلب مسئولیت: پادکست و آثار هنری تعبیه شده در این صفحه متعلق به Peter Liu است که متعلق به صاحب آن است و به Listen Notes، Inc وابسته یا تایید نشده است.