Upgrade to Pro
— share decks privately, control downloads, hide ads and more …
Speaker Deck
Features
Speaker Deck
PRO
Sign in
Sign up for free
Search
Search
CTRオンライン予測システムのアーキテクチャ
Search
Yoshitomo Hayashi
September 27, 2017
Technology
2
4.2k
CTRオンライン予測システムのアーキテクチャ
「Ameba広告システムの裏側見せます - オレシカナイトvol3」発表資料です。
https://cyberagent.connpass.com/event/64176/
Yoshitomo Hayashi
September 27, 2017
Tweet
Share
More Decks by Yoshitomo Hayashi
See All by Yoshitomo Hayashi
Ameba DSPのOpen-Auctionにおける入札戦略
yyhayashi303
2
2.8k
進化する配信ロジックとDSP戦略
yyhayashi303
1
160
モブプロ導入で見えてきた効果@オレシカナイト
yyhayashi303
1
1k
CircuitBreakerの適用
yyhayashi303
0
1.6k
Other Decks in Technology
See All in Technology
Turing × atmaCup #18 - 1st Place Solution
hakubishin3
0
480
KubeCon NA 2024 Recap / Running WebAssembly (Wasm) Workloads Side-by-Side with Container Workloads
z63d
1
240
組織に自動テストを書く文化を根付かせる戦略(2024冬版) / Building Automated Test Culture 2024 Winter Edition
twada
PRO
13
3.7k
.NET 9 のパフォーマンス改善
nenonaninu
0
860
なぜCodeceptJSを選んだか
goataka
0
160
Wantedly での Datadog 活用事例
bgpat
1
440
ブラックフライデーで購入したPixel9で、Gemini Nanoを動かしてみた
marchin1989
1
530
GitHub Copilot のテクニック集/GitHub Copilot Techniques
rayuron
31
12k
Fanstaの1年を大解剖! 一人SREはどこまでできるのか!?
syossan27
2
160
2024年にチャレンジしたことを振り返るぞ
mitchan
0
140
Jetpack Composeで始めるServer Cache State
ogaclejapan
2
170
コンテナセキュリティのためのLandlock入門
nullpo_head
2
320
Featured
See All Featured
Done Done
chrislema
181
16k
Learning to Love Humans: Emotional Interface Design
aarron
273
40k
Reflections from 52 weeks, 52 projects
jeffersonlam
347
20k
Unsuck your backbone
ammeep
669
57k
Measuring & Analyzing Core Web Vitals
bluesmoon
4
170
Code Reviewing Like a Champion
maltzj
520
39k
Rails Girls Zürich Keynote
gr2m
94
13k
Exploring the Power of Turbo Streams & Action Cable | RailsConf2023
kevinliebholz
28
4.4k
Building a Modern Day E-commerce SEO Strategy
aleyda
38
7k
Music & Morning Musume
bryan
46
6.2k
Designing Dashboards & Data Visualisations in Web Apps
destraynor
229
52k
What’s in a name? Adding method to the madness
productmarketing
PRO
22
3.2k
Transcript
CTRΦϯϥΠϯ༧ଌ γεςϜͷΞʔΩςΫνϟ ΦϨγΧφΠτvol.3 גࣜձࣾαΠόʔΤʔδΣϯτ ྛ ۍ๎
ࣗݾհ ྛɹۍ๎ʢ͠Α͠ͱʣ αʔόʔαΠυΤϯδχΞ 2011 αΠόʔΤʔδΣϯτೖࣾ ೖࣾޙ͍͔ͭ͘ͷwebαʔϏε୲ 2015͔ΒMDHͰ৴ϩδοΫͷվળ
ࣗݾհ झຯ ίʔώʔ ՈͰυϦοϓͨ͠Γ ίʔϧυϒϦϡʔ࡞ͬͨΓ Netflix Ξχϝ ΥʔΩϯάɾσου
CTRΦϯϥΠϯ༧ଌ γεςϜͷΞʔΩςΫνϟ
CTRͱʁ
CTRͱ? CTRʢΫϦοΫʣ CTR = Click / Impression
ͳͥ༧ଌ͕ඞཁͳͷ͔ʁ
ࠂͷऩӹ ΫϦοΫ՝ۚ ࠂ1ΫϦοΫ͋ͨΓʓʓԁʢCPCʣ
ࠂͷऩӹ ΫϦοΫ՝ۚ ࠂ1ΫϦοΫ͋ͨΓʓʓԁʢCPCʣ ΑΓΫϦοΫ͞ΕΔ CPC͕ߴ͍ࠂΛ৴͍ͨ͠
ࠂΛϥϯΩϯά CTR × CPCʹΑΔϥϯΩϯά CTRόϯσΟοτΞϧΰϦζϜͰࢉग़ ࣮ͷimp, clickΛ༻ ࣮ͷूܭ [ࠂ ×
Ϣʔβʔଐੑ × ࠂ] ຖʹimp, clickΛܭଌ
͜Ε·ͰͷϥϯΩϯάͷ՝ ࣮͕গͳ͍߹ʹ͏·͘࠷దԽ͞Εͳ͍ Ϣʔβʔຖʹ࠷దͳࠂΛ৴ग़དྷ͍ͯͳ͍
ػցֶशʹΑΔCTR༧ଌ ଟ͘ͷૉੑΛՃՄೳ ࣮͕গͳͯ͋͘Δఔ༧ଌՄೳ ύʔιφϥΠζ͞ΕͨϥϯΩϯά
։ൃମ੍ ॳظ γεςϜΤϯδχΞ2ਓ σʔλαΠΤϯςΟετ1ਓʢळ༿ݪϥϘʣ ݱࡏ γεςϜΤϯδχΞ2ʙ3ਓ σʔλαΠΤϯςΟετ2ਓʢळ༿ݪϥϘ1ਓʣ
ΞʔΩςΫνϟ
ΞʔΩςΫνϟ ֶशσʔλ JoinࡁΈͷ ϩά ϩά ϩά ػցֶश ϝτϦΫε Ϟσϧ ϑΝΠϧ
Ϟσϧ ϑΝΠϧ Stream Aggregator Data Joiner Learner Predictor ModelStore
Data-Joiner
Data-Joinerͷׂ ࠂ͕click͞Ε͔ͨͲ͏͔Λఆ͢Δ imp౸ୡޙɺҰఆظؒclickͷ౸ୡΛͭ impͱclickͷσʔλͷࠩҟΛແ͘͢ refererͷʹࠩҟ͕͋ͬͨ
Apache IgniteΛ༻࣮ͨ͠ Event Notifications imp click Stream Data Joiner Aggregator
Apache IgniteΛ༻࣮ͨ͠ Event Notifications put-event impͷ߹ TTLΛ5ʹઃఆ͠อଘ imp click Stream
Data Joiner Aggregator
Apache IgniteΛ༻࣮ͨ͠ Event Notifications put-event impͷ߹ TTLΛ5ʹઃఆ͠อଘ put-event clickͷ߹ରԠ͢Δ impΛݕࡧ͠click͞Εͨ
impͱͯ͠Aggregatorʹૹ৴ imp click Stream Data Joiner Aggregator
Apache IgniteΛ༻࣮ͨ͠ Event Notifications put-event impͷ߹ TTLΛ5ʹઃఆ͠อଘ put-event clickͷ߹ରԠ͢Δ impΛݕࡧ͠click͞Εͨ
impͱͯ͠Aggregatorʹૹ৴ expired-event 5ܦͬͯclick͕དྷͳ͍ ߹click͞Εͳ͔ͬͨimpͱ ͯ͠Aggregatorʹૹ৴ imp click Stream Data Joiner Aggregator
Aggregator
Aggregatorͷׂ ֶशʹඞཁͳσʔλΛऩू ϩά͔Βऔಘग़དྷΔͷ ϩά͔ΒऔಘͰ͖ͳ͍ͷ ऩूͨ͠σʔλΛLearnerʹૹΔ σʔλαϯϓϦϯά͠100݅ͣͭ
ϩά͔ΒऔಘՄೳͳσʔλ Ϣʔβʔͷใ UA, IPΞυϨε, referer, ϦλήϢʔβʔ͔ etc. ࠂͷใ ۀछID, ࠂओID,
ΫϦΤΠςΟϒID etc. ໘ͷใ ࠂID, ϝσΟΞID etc.
ϩά͔ΒऔಘෆՄೳͳσʔλ Ϣʔβʔͷใ σϞάϥʢੑผɾྸʣ ಠࣗʹ࡞ͨ͠ૉੑ ߦಈཤྺΛϕʔεʹͨ͠ϢʔβʔΫϥελ ࠂςΩετΫϥελ
Learner
Learnerͷׂ Aggregator͔Βड͚औͬͨσʔλΛ༻͠ϞσϧΛߏங͢Δ ϞσϧΛߏங͢ΔίΞ෦C++ʢσʔλαΠΤϯςΟ ετ୲ʣ 15ִؒͰϞσϧΛߋ৽ ϞσϧϑΝΠϧͰϞσϧετΞʢS3ʣʹอଘ ػցֶशϝτϦΫεʢauroc, logloss etc.ʣΛDBʹอଘ
Learner͕ੜ͢Δ ϞσϧϑΝΠϧ ֶश༻ϚελϑΝΠϧʢ12ִ࣌ؒؒͰߋ৽ʣ Learner͜ͷϑΝΠϧΛ༻ֶͯ͠श͢Δ ༧ଌ༻ϚελϑΝΠϧʢ12ִ࣌ؒؒͰߋ৽ʣ Predictor͕CTRΛ༧ଌ͢Δࡍʹ༻͢Δ ༧ଌ༻ύονϑΝΠϧ ༧ଌ༻ϚελϑΝΠϧ͔ΒͷࠩϑΝΠϧ ͜ͷϑΝΠϧ͕LearnerʹΑͬͯ15ִؒͰߋ৽͞ΕΔ
Predictor
Predictor ༧ଌʹඞཁͳσʔλΛड͚औΓ༧ଌCTRΛฦ͢API 15ִؒͰϞσϧετΞ͔Β࠷৽ͷϞσϧϑΝΠ ϧΛऔಘ͠ߋ৽͢Δ
༧ଌ͕։࢝ग़དྷΔ·Ͱ ىಈ࣌ʹϚελϑΝΠϧΛಡΈࠐΉ ϚελϑΝΠϧಡΈࠐΈޙ͔Β༧ଌՄೳ ϚελϑΝΠϧͷ࠷ऴߋ৽͔࣌Βͷࠩύον ϑΝΠϧΛద༻͍ͯ͘͠ʢ࠷େͰ47ϑΝΠϧʣ 1ύονϑΝΠϧ5ʙ6ඵͰద༻ՄೳͳͷͰɺ5 ҎͰྃ
CTR༧ଌγεςϜಋೖޙ
CPMൺֱ ϥϯμϜ ࣮CTR ༧ଌCTR ࣮CTRରൺ7ˋվળ ϥϯμϜରൺ50ˋվળ
CTRൺֱ ࣮CTRରൺ6ˋվળ ϥϯμϜରൺ8ˋվળ ϥϯμϜ ࣮CTR ༧ଌCTR
͓·͚
Real-Time Optimizer ʢROʣ
Real- Time OptimizerʢROʣ 20176݄ϦϦʔε ඪCPAʹ߹ΘͤͯCPCΛࣗಈௐ͢Δ
CPCͷࢉग़ํ๏ CPC = ඪCPA × CVR ඪCPA 1CVಘΔͷʹࢧͬͯྑ͍අ༻ ࠂओ͕ܾఆ CVRʢίϯόʔδϣϯʣ
CV / Click
͜Ε·ͰͷCVRࢉग़ํ๏ աڈ࣮ΛݩʹώϡʔϦεςΟοΫͳCVRࢉग़ ࠂ × ΞΧϯτຖʹCVRΛࢉग़ ϦλήϢʔβʔͷ߹ิਖ਼Ϩʔτ
ݱঢ়ͷ՝ CV͕ग़ʹ͍͘Ҋ݅ͷ߹ʹCVRͷਫ਼͕ѱ͍ ৽نΞΧϯτͷ߹࣮͕ແ͍ ۀछશମͷ࣮Λࢀর ৽نࠂͷ߹ʹ࣮͕ͳ͍ ࠂάϧʔϓͷ࣮Λࢀর
CTR༧ଌγεςϜͷࢿ࢈Λ ׆༻ͨ͠CVR༧ଌγεςϜ
CVR༧ଌγεςϜ Ϟσϧͷߏங࣍όονʢBatch-Learnerʣ Clickൃੜ͔ΒCVൃੜ·Ͱͷ͕͍࣌ؒͷͰϦΞ ϧλΠϜͰֶश͠ͳ͍ LearnerͷίΞ෦ɺੜ͞ΕΔϞσϧϑΝΠ ϧɺPredictorͦͷ··༻
ΞʔΩςΫνϟ Predictor ModelStore Batch-Learner ϞσϧϑΝΠϧ ϞσϧϑΝΠϧ ػցֶश ϝτϦΫε ֶशσʔλ
CVR༧ଌͷঢ়گ ༧ଌCVR ࣮CVR ࣮CVRରൺ3ˋվળ
͝ਗ਼ௌ͋Γ͕ͱ͏͍͟͝·ͨ͠