Lock in $30 Savings on PRO—Offer Ends Soon! ⏳
Speaker Deck
Features
Speaker Deck
PRO
Sign in
Sign up for free
Search
Search
広告配信サーバーと広告配信比率最適化問題
Search
Ken Wagatsuma
February 10, 2018
Technology
1
1k
広告配信サーバーと広告配信比率最適化問題
Lightening Talk at
https://techconf.cookpad.com/2018/
Ken Wagatsuma
February 10, 2018
Tweet
Share
More Decks by Ken Wagatsuma
See All by Ken Wagatsuma
Pregel Graph Compute Engines - Supersteps Exampls
kenju
0
220
Kafka on Kubernetes with Strimzi
kenju
0
180
AWS DynamoDB Accelerator (DAX) 101
kenju
2
7.2k
Moden browser introduction
kenju
1
430
Cookpad summer internship 2019 - API
kenju
0
10k
Introduction to Design Patterns
kenju
0
99
GraphQL Asia 2019 "Re-architecture of a decade-old app with BFF/GraphQL"
kenju
0
9k
Introduction to TypeScript
kenju
0
750
Introduction to Programmatic Ad
kenju
0
270
Other Decks in Technology
See All in Technology
“決まらない”NSM設計への処方箋 〜ビットキーにおける現実的な指標デザイン事例〜 / A Prescription for "Stuck" NSM Design: Bitkey’s Practical Case Study
bitkey
PRO
1
520
Uncertainty in the LLM era - Science, more than scale
gaelvaroquaux
0
710
モバイルゲーム開発におけるエージェント技術活用への試行錯誤 ~開発効率化へのアプローチの紹介と未来に向けた展望~
qualiarts
0
530
【CEDEC+KYUSHU2025】学生・若手必見!テクニカルアーティスト 大全 ~仕事・スキル・キャリアパス、TAの「わからない」を徹底解剖~
cygames
PRO
0
130
GitLab Duo Agent Platformで実現する“AI駆動・継続的サービス開発”と最新情報のアップデート
jeffi7
0
200
「Managed Instances」と「durable functions」で広がるAWS Lambdaのユースケース
lamaglama39
0
180
なぜフロントエンド技術を追うのか?なぜカンファレンスに参加するのか?
sakito
10
2k
Docker, Infraestructuras seguras y Hardening
josejuansanchez
0
150
生成AI・AIエージェント時代、データサイエンティストは何をする人なのか?そして、今学生であるあなたは何を学ぶべきか?
kuri8ive
2
2k
著者と読み解くAIエージェント現場導入の勘所 Lancers TechBook#2
smiyawaki0820
11
5.5k
AI時代におけるアジャイル開発について
polyscape_inc
0
120
新 Security HubがついにGA!仕組みや料金を深堀り #AWSreInvent #regrowth / AWS Security Hub Advanced GA
masahirokawahara
0
110
Featured
See All Featured
Fireside Chat
paigeccino
41
3.7k
Build The Right Thing And Hit Your Dates
maggiecrowley
38
3k
A designer walks into a library…
pauljervisheath
210
24k
Git: the NoSQL Database
bkeepers
PRO
432
66k
Easily Structure & Communicate Ideas using Wireframe
afnizarnur
194
17k
Mobile First: as difficult as doing things right
swwweet
225
10k
The Success of Rails: Ensuring Growth for the Next 100 Years
eileencodes
47
7.8k
Measuring & Analyzing Core Web Vitals
bluesmoon
9
700
A better future with KSS
kneath
240
18k
BBQ
matthewcrist
89
9.9k
Responsive Adventures: Dirty Tricks From The Dark Corners of Front-End
smashingmag
253
22k
The Hidden Cost of Media on the Web [PixelPalooza 2025]
tammyeverts
1
88
Transcript
ࠂ৴αʔόʔͱ ࠂ৴ൺ࠷దԽ ϝσΟΞϓϩμΫτ։ൃ෦ ,FOKV8BHBUTVNB
8IP Kenju Wagatsuma (github.com/kenju) • ϝσΟΞϓϩμΫτ։ൃ෦ • αʔόʔαΠυΤϯδχΞ • ͖ͳͷɿRuby,
ίʔώʔ, ϩδΧϧΫοΩϯά • ݏ͍ͳͷɿ1ϲ݄લʹॻ͍ͨࣗͷίʔυ
ϝσΟΞϓϩμΫτ։ൃ෦ ୲αʔϏεɿ ࠂ৴, storeTV, cookpadTV, OEM, ͦͷଞଟ ࢀߟɿ ։ൃऀϒϩάʰΫοΫύουͷࠂΤϯδχΞԿΛ ͍ͬͯΔͷ͔ʱ
ຊ͍ͨ͜͠ͱɻ ϝσΟΞϓϩμΫτ։ൃ෦Ͱ ͲΜͳϓϩδΣΫτΛ͍ͬͯΔͷ͔ʁ
νʔϜʹೖͬͯϲ݄ޙʹऔΓΜͩϓϩδΣΫτ ΫοΫύουͷࠂ৴αʔόʔʹ͓͚Δ ࠂ৴ൺͷࣗಈ࠷దԽϓϩδΣΫτɻ
ݫ͍͠εέδϡʔϧ • ϝσΟΞϓϩμΫτ։ൃ෦δϣΠϯ - 10݄த० • ͓खฒΈഈݟϓϩδΣΫτ - ~11݄த० •
৴࠷దԽτϥΠΞϧ - 12/4(݄) 10:00 - 12/11(݄) 10:00 ???
ղܾ͍ͨ͠՝ • ʑͷखӡ༻ʹΑΔνϡʔχϯά͕ඞཁ - => ࡞ۀ͕ൃੜ • ӡ༻ऀͷܦݧͱצʹཔͬͨνϡʔχϯά - =>
ҟಈ࣌ಋೖ࣌ͷίετ͕ߴա͗ • ࠷దͳࡏݿൺΛࣗಈͰௐͰ͖ͳ͍ - => ࠂܝग़ͷػձଛࣦ
Ͳ͏ղܾ͢Δ͔ • ࡏݿׂྔͱ࣮͔Β࠷దͳ৴ൺͷิ ਖ਼Λߦ͏ - ΠϯϓϨογϣϯϕʔε͔ΒΫϦοΫϕʔεͷ৴ - ΫϦοΫ༧ଌΛར༻ͨ͠ൺͷࣗಈ࠷దԽ - ϦΞϧλΠϜूܭσʔλΛ׆༻ͨ͠ΞʔΩςΫνϟ
‣ Lambda Architecture ʹ͓͚Δ Speed Layer
l4QFFE-BZFSzPO"84 • Kinesis, DynamoDB, Lambda Λ׆༻ͨ͠ Speed Layer (from Lambda
Architecture) • طଘͷετϦʔϜʹɺΫ ϦοΫܭࢉϨΠϠʔΛ Ճ͚ͨͩ͠ = ઌਓͷݞ ʹΔ
ৄ͍ͪ͜͠Β ࢀߟɿ ʰCookpad Tech Kitchen #9 ʙ1ߦͷϩάͷ͜͏ ଆʙ Λ։࠵͠·ͨ͠ʂʱ
ΫϦοΫ༧ଌ͍͠ʂʂʂ • ޯϒʔεςΟϯάܾఆʢGBDTʣΛ༻͍ͨࠂ͝ͱͷΫϦοΫ༧ଌ - Facebook https://code.facebook.com/posts/975025089299409/evaluating-boosted-decision-trees-for-billions-of-users - SmartNews https://speakerdeck.com/komiya_atsushi/gbdt-niyorukuritukulu-yu-ce-wogao-su-hua-sitai-number-oresikanaito-vol-dot-4 •
ଟόϯσΟοτͷҰछͰ͋ΔMortal Multi-Armed BanditsͷԠ༻ - Voyage Group http://techlog.voyagegroup.com/entry/2015/04/03/114547ɹ • Neural Networkͷ૯߹֨ಆٕʢ͕͢͞Googleʣ - Google http://www.eecs.tufts.edu/~dsculley/papers/ad-click-prediction.pdfɹ • ৴པͱ࣮ͷϩδεςΟοΫճؼʢୠܻ͕͠ԯϨϕϧʣ - Criteo http://olivier.chapelle.cc/pub/ngdstone.pdfɹ
ؒʹ߹Θͳ͍ʂ • τϥΠΞϧͳΜͱͯ͠ʹ࣮ࢪ͍ͨ͠ - վળͷαΠΫϧΛճͨ͢Ί • QCDͰݴ͏ͳΒɺDelivery, QualityΛ༏ઌ - ͳΜͱͯؒ͠ʹ߹Θ͍ͤͨʂ
• ࠷ॳ͔Βᘳͳਫ਼༧ଌ·ͣෆՄೳ - ػցֶशͰղܾ͠ͳͯ͘Α͍͔·ͣߟ͑Δ - ࢀߟɿʰࣄͰ͡ΊΔػցֶशʱ
ҠಈฏۉԞ͕ਂ͍ • SMA (Simple Moving Average) = ۙ N ݸͷॏΈ͚ͷͳ͍୯७ͳฏۉ
• WMA (Weighted Moving Average) = ΑΓ࠷ۙͷσʔλʹॏΈ͚ • EWMA (Exponentially Weighted Moving Average) = ࢦؔతʹॏΈ͚ • MMA (Modified Moving Average) = EWMAͷѥछ ଞʹTriangle MA, Sine Weighted MA, KZ Filtering,...etc ࢀߟɿhttps://en.wikipedia.org/wiki/Moving_average#Simple_moving_averag
աڈϩάΛݩʹΞϧΰϦζϜͷਫ਼Λੳ • Jupyter Notebook / Python - ࢀߟɿ։ൃऀϒϩάʰRailsΤϯ δχΞʹཱͭJupyter Notebook
ͱiRubyʱ • ൺֱͨ͠ΞϧΰϦζϜ - Total Average - Cumulative Average - Simple Moving Average (3 Hours) - Simple Moving Average (6 Hours)
τϥΠΞϧ݁Ռ • ิਖ਼ͷϩδοΫʹ՝ ͕ݟ͔ͭͬͨ ͷɺτϥΠΞϧͱ͠ ͯޭ
ظతνϡʔχϯά • Speed Layer ͷ࠶ઃܭɾຏ͖ࠐΈ - ετϦʔϜॲཧʹԊͬͨσʔλͷྲྀΕ • ෛ࠴ =
ະୡ ΛՃຯͨ͠ϩδοΫ - ୈҰ࣍τϥΠΞϧΛ͍ͬͯͳ͔ͬͨΒݟ͑ͳ͔ͬͨ՝ • ҠಈฏۉΞϧΰϦζϜͷվળ - Batch LayerͰΦϑϥΠϯͰܭࢉ&࠷ਫ਼͕ྑ͍ͷΛબ - Gem࡞ͬͨ https://github.com/kenju/moving_avg-ruby
தظͰ͍͖ͬͯ • ΫϦοΫ༧ଌਫ਼ͷߋͳΔ্ˍ৽نࠂ։ൃ - ػցֶशϨΠϠʔͷຊ൪ಋೖ • Lambda Architectureͷຏ͖ࠐΈ - ࢀߟɿ։ൃऀϒϩάʰαʔόʔϨεͳόοΫΞοϓγεςϜ
Λ AWS SAM Λ༻͍ͯγϡοͱߏங͢Δʱ • ࠂ৴αʔόʔࣗମͷѹతվળ - ։ൃج൫ͷڥඋ - ύϑΥʔϚϯε࠷దԽɺϨΨγʔίʔυͷվળ
ຖͷྉཧΛָ͠Έʹ͢Δ 5IBOLZPV