Slides: Recsys Keynote: Improving Recommendation Systems & Search in the Age of LLMs - Eugene Yan, Amazon

Source Video

Recsys Keynote: Improving Recommendation Systems & Search in the Age of LLMs - Eugene Yan, Amazon

Relationship To World's Fair 2026

These slides are extracted from a public AI Engineer YouTube video connected to World's Fair 2026. Speaker-matched clips are supporting context unless later confirmed as exact session recordings; official livestream recordings are day-level/event-level source material.

Related Scheduled Sessions

• No individual scheduled session mapping has been assigned yet; treat this as an event livestream deck.

Extracted Slides

OCR text:

aWS

ee)

@®Graphite W Windsurf 4 Moneobe

#Mdaily £3augmentcode WorkOS

OCR text:

Improving RecSys & Search

with LLM techniques

Al Engineer World's Fair 2025, RecSys Track

with Latte & Mochi Sy

| a Microsoft ary?

OCR text:

Enriching exploratory search queries @ Spotify

( Extract from catalog titles, | pe eu ae aw asa eeuaune RuaTseeyaes FeTseMn wane CE eMEEEEREEEETEeEremNErEeEEEEETE Ag

playlist names, podcasts —! | Setreguiar, ‘ Query rank optimized for ) :

— ae i | existing results stream, add-to-playlist, etc | |

| Mine from search logs weuessuesuecgphponssacsszssseeseeeeesssecssusssessensnes puserssssesneseanoesee?

[ vse user's recent ; =

searches & saved items |

f Apply metadata expansion

[ rules (<artist> + “cover”)

- Apply LLMs to generate

A sf | natural language queries 7

ja Doc2Query, InPars ;

- ; ra)

a cS 0008

OCR text:

TL;DR:We buit a transformer-based

works.

Foryears,Stripe has been usngmachineleamingmodels trained on

AIE

dscretefeatures(BIN，p,paymentmetod,et.）to mprove our

products forusers.And these feature-by-feature effortshave worked

wll+15%coveron-30%fraud

But these models have Imitations.Wehave to select and therefore

Aside:Worked for

constrain thefeatures considered bythemode.Andeachmodel

equrestask-specifictrainingforauhorization,forfraud,fordsputes,

Given theleamingpower ofgenerallzed transfomerarchitectures,we

andsoon.

paymentsandfraud

obviousthati would-payments islikelanguagein some ways

wonderedwhetheranLLM-stye approachcould workhere.t wasnt

(structuralpattemssmlarto sytaxandsemantics,temporaly

atStripetoo!

knsywnainglent

sequential)and extremely unlike language inothers (fewer distinct

grammaticalrules).

Sowebuitapaymentsfoundatonmodelsef-supevisednewok

thatleamsdense,enerl-puposevctorsforeveytransactnmuch

transactionsitdistillseachchargeskynasintoaingeeatl

mbedsin.

aws

Slide-Derived Subjects To Review

Subject extraction uses video title, related session titles/descriptions, transcript context, and OCR text when available. OCR is best-effort and should be reviewed against the embedded slide images.