Data Science in the Wild

Est. audience

100

Apple rating

0 from 0

Cadence

Daily

Latest

2026-11-02

By

Peter Liu

Based on

12 recent episodes

• Covers: Production machine learning systems, LLM evaluation, causal inference, recommender systems, and experimentation from major tech companies.
• For: Data scientists, machine learning engineers, and technical product teams building production systems.
• Best for: Practitioners wanting real technical case studies of shipping machine learning in production.
• Skip if: Non-technical professionals or business leaders looking for high-level AI overviews.

Start with

• Spotify — Can You Ship an LLM Change on Evals Alone?: How to determine if offline LLM evaluations reliably predict online A/B testing results.
• iFood — Predicting the Discount That Tips a Customer: Using a 4B-parameter LLM as an uplift model to optimize customer discount allocations.
• WeChat — Generative Retrieval for Industrial Search: Implementing generative retrieval and semantic IDs to improve search conversion and compute efficiency.

Visit

Summarised by AI from 12 recent episodes. Audience estimate and Apple rating from Podscan, checked 2026-11-03; treat the estimate as a guide and ask the show for its own numbers. Prices are not included. Report a mistake.