Leemay Nassery
where else to find them
what they talk about
all 6 in the filters
where they keep going back
- Strange Loop2 editions2018–2023
all 5 in the filters
on a stage with
- Emily Samuelsonce
- Matthew Hawthorneonce
who talks about the same things
- Kevin Goldsmith12 talks
- Gojko Adzic31 talks
- Cat Swetel9 talks
- Charles Sonigo4 talks
- Hazel Weakly10 talks
- Marcin Szymaniuk11 talks
| title | conference | date |
|---|---|---|
| The choice is yours – or is it? | LeadDev New York 2024 | 2024-09-04 |
Decision-making examples land on specifics: a platform team at Spotify consolidates distributed filtering logic into an existing backend service consolidation… | ||
| Experimentation: putting research papers into prod | PWLConf 2023 | 2023-09-21 |
Claims specific enough to act on: interleaving is two orders of magnitude more sensitive than classic A/B for ranking, but requires an abstraction library plus… | ||
| Experimentation: putting research papers into prod | Strange Loop 2023 | 2023-09-21 |
Claims that interleaving yields two orders of magnitude more sensitivity than classic A/B testing and that Netflix Amazon and Airbnb use interleaved… | ||
| Risky business: taking risks in production | LeadDev Live 2020 | 2020-04-07 |
Comcast X1 ships a new personalized "For You" experience built from Spark jobs, web services and Couchbase, validated with A/B testing, rollout via canaries… | ||
| X1 Recommendations Platform: Started from the bottom.. | TWIMLcon: AI Platforms 2019 | 2019-10-01 |
Comcast rebuilds X1 recommendations by replacing brittle HDFS + daily copies and Lambda handlers with a fleet of Flink jobs consuming Kafka/Kinesis and… | ||
| Resurrecting a Recommendations Platform | Strange Loop 2018 | 2018-09-26 |
Built a GPU-backed deep learning recommender while migrating a bare‑metal platform to AWS, keeping millions served. Replaces an 18‑hour batch transform with an… | ||
| nothing matches | ||