INFORMAZIONI SU QUESTO EPISODIO

Inglese
Stati Uniti

TRASCRIZIONE 🔗

CERCA TRA GLI EPISODI PASSATI

Cerca gli episodi passati di Data Science in the Wild.

ALTRI EPISODI IN QUESTO PODCAST

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…
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–…
LCM-Promo (Prosus and iFood) turns a 4B-parameter LLM into an uplift model for discounts. In a one-month A/B test on churned users it lifted conversion 1% and cut promotion cost 6% vs. the old policy. Key takeaways: Discounts as tokens. Each prompt holds session context (day, lunch or dinner shift…
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…
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…
Dichiarazione di non responsabilità: Il podcast e la grafica incorporati in questa pagina provengono da Peter Liu, che è di proprietà del suo proprietario e non è affiliato o approvato da Listen Notes, Inc.